Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.3203. Min Act: -0.1700
Data Index: 5209203 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.2578. Min Act: -0.1700
Data Index: 4675412 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.1953. Min Act: -0.1700
Data Index: 3685192 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.1015. Min Act: -0.1700
Data Index: 4688489 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.1015. Min Act: -0.1700
Data Index: 8509356 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.1328. Min Act: -0.1700
Data Index: 8432173 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.0703. Min Act: -0.1700
Data Index: 1627942 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.0390. Min Act: -0.1700
Data Index: 4785294 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.9765. Min Act: -0.1700
Data Index: 3955769 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.0078. Min Act: -0.1700
Data Index: 977617 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3203. Min Range: -7.3203
Max Act: 7.0078. Min Act: -0.1700
Data Index: 1683815 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.9765. Min Act: -0.1700
Data Index: 2910368 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.9453. Min Act: -0.1700
Data Index: 7596424 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.9453. Min Act: -0.1700
Data Index: 7313613 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.9140. Min Act: -0.1700
Data Index: 5341542 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.8828. Min Act: -0.1700
Data Index: 1639160 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.8515. Min Act: -0.1700
Data Index: 4168701 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.8515. Min Act: -0.1700
Data Index: 4982481 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.8515. Min Act: -0.1700
Data Index: 3449441 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3203. Min Range: -7.3203
Max Act: 6.8203. Min Act: -0.1700
Data Index: 7221833 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19