Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.6536. Min Act: -0.1700
Data Index: 6796529 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.4036. Min Act: -0.1700
Data Index: 8185116 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.4661. Min Act: -0.1700
Data Index: 5445327 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.3411. Min Act: -0.1700
Data Index: 3647088 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.3411. Min Act: -0.1700
Data Index: 5501337 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.2786. Min Act: -0.1700
Data Index: 8634924 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.2786. Min Act: -0.1700
Data Index: 6739675 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.3411. Min Act: -0.1700
Data Index: 8135801 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.2786. Min Act: -0.1700
Data Index: 3206599 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.2161. Min Act: -0.1700
Data Index: 5935453 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0911. Min Act: -0.1700
Data Index: 2105524 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.1536. Min Act: -0.1700
Data Index: 7130913 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0911. Min Act: -0.1700
Data Index: 1698286 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.1536. Min Act: -0.1700
Data Index: 7451245 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.2161. Min Act: -0.1700
Data Index: 7077175 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0286. Min Act: -0.1700
Data Index: 4067995 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0911. Min Act: -0.1700
Data Index: 1066734 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0911. Min Act: -0.1700
Data Index: 4629749 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0911. Min Act: -0.1700
Data Index: 4107360 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6536. Min Range: -10.6536
Max Act: 10.0911. Min Act: -0.1700
Data Index: 1415613 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19