Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.5629. Min Act: -0.1700
Data Index: 5212757 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.5004. Min Act: -0.1700
Data Index: 4947670 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.4379. Min Act: -0.1700
Data Index: 6376605 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.2504. Min Act: -0.1700
Data Index: 613965 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1879. Min Act: -0.1700
Data Index: 236275 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1879. Min Act: -0.1700
Data Index: 4194889 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1879. Min Act: -0.1700
Data Index: 1143249 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1879. Min Act: -0.1700
Data Index: 3149241 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1254. Min Act: -0.1700
Data Index: 5547607 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1567. Min Act: -0.1700
Data Index: 3924119 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1567. Min Act: -0.1700
Data Index: 1693713 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1567. Min Act: -0.1700
Data Index: 2864606 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1567. Min Act: -0.1700
Data Index: 1367784 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1567. Min Act: -0.1700
Data Index: 5354729 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1254. Min Act: -0.1700
Data Index: 5989914 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.1567. Min Act: -0.1700
Data Index: 8429851 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.0942. Min Act: -0.1700
Data Index: 7328813 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.0942. Min Act: -0.1700
Data Index: 2330609 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.0629. Min Act: -0.1700
Data Index: 2117157 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5629. Min Range: -6.5629
Max Act: 6.0629. Min Act: -0.1700
Data Index: 5196678 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19