Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.4416. Min Act: -0.1700
Data Index: 3234343 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.3478. Min Act: -0.1700
Data Index: 1923885 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.2541. Min Act: -0.1700
Data Index: 8781416 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.2228. Min Act: -0.1700
Data Index: 781018 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.1916. Min Act: -0.1700
Data Index: 7493109 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.1291. Min Act: -0.1700
Data Index: 5541474 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.0978. Min Act: -0.1700
Data Index: 3222475 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.0353. Min Act: -0.1700
Data Index: 7184737 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.0353. Min Act: -0.1700
Data Index: 5304746 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4416. Min Range: -6.4416
Max Act: 6.0666. Min Act: -0.1700
Data Index: 8284654 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9728. Min Act: -0.1700
Data Index: 5562567 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9728. Min Act: -0.1700
Data Index: 2178469 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9728. Min Act: -0.1700
Data Index: 599555 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9103. Min Act: -0.1700
Data Index: 5858435 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9103. Min Act: -0.1700
Data Index: 8300220 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9103. Min Act: -0.1700
Data Index: 7165902 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9103. Min Act: -0.1700
Data Index: 8641984 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.9103. Min Act: -0.1700
Data Index: 8317104 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.8791. Min Act: -0.1700
Data Index: 7864591 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4416. Min Range: -6.4416
Max Act: 5.8791. Min Act: -0.1700
Data Index: 2012748 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19