Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 2938731 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.9448. Min Act: -0.1700
Data Index: 4887923 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.8823. Min Act: -0.1700
Data Index: 1902017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.8510. Min Act: -0.1700
Data Index: 1679676 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7885. Min Act: -0.1700
Data Index: 7584503 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.8198. Min Act: -0.1700
Data Index: 6131831 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7573. Min Act: -0.1700
Data Index: 837446 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 4589799 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 7280155 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.6948. Min Act: -0.1700
Data Index: 5307208 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 3694458 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 3592340 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 7144227 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 368163 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 4333262 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.7260. Min Act: -0.1700
Data Index: 8447259 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.6948. Min Act: -0.1700
Data Index: 652641 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.6948. Min Act: -0.1700
Data Index: 6093157 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.6948. Min Act: -0.1700
Data Index: 3144029 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9448. Min Range: -4.9448
Max Act: 4.6948. Min Act: -0.1700
Data Index: 784668 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19