Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.6661. Min Act: -0.1700
Data Index: 5944280 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.3848. Min Act: -0.1700
Data Index: 8468386 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.3223. Min Act: -0.1700
Data Index: 1657243 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.1661. Min Act: -0.1700
Data Index: 4768054 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.1348. Min Act: -0.1700
Data Index: 6946325 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.1348. Min Act: -0.1700
Data Index: 6638301 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.1348. Min Act: -0.1700
Data Index: 2155238 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.1036. Min Act: -0.1700
Data Index: 3603137 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.0723. Min Act: -0.1700
Data Index: 323342 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.0411. Min Act: -0.1700
Data Index: 8538488 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.0723. Min Act: -0.1700
Data Index: 6289137 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6661. Min Range: -7.6661
Max Act: 7.0098. Min Act: -0.1700
Data Index: 445708 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.9786. Min Act: -0.1700
Data Index: 2453219 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.9786. Min Act: -0.1700
Data Index: 8535685 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.8848. Min Act: -0.1700
Data Index: 3507024 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.9161. Min Act: -0.1700
Data Index: 384861 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.8848. Min Act: -0.1700
Data Index: 4797217 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.8536. Min Act: -0.1700
Data Index: 6817293 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.8848. Min Act: -0.1700
Data Index: 5882379 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6661. Min Range: -7.6661
Max Act: 6.8536. Min Act: -0.1700
Data Index: 3633152 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19