Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0214. Min Range: -6.0214
Max Act: 6.0214. Min Act: -0.1700
Data Index: 5530781 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.9276. Min Act: -0.1700
Data Index: 1985002 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.9276. Min Act: -0.1700
Data Index: 3861969 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1601952 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1771426 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 483337 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 2654695 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 5788517 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 4118557 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 3203348 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 6364392 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8651. Min Act: -0.1700
Data Index: 3184484 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8964. Min Act: -0.1700
Data Index: 5892494 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 6685274 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 642347 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 3133656 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 278489 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8026. Min Act: -0.1700
Data Index: 5842233 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8339. Min Act: -0.1700
Data Index: 4504388 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0214. Min Range: -6.0214
Max Act: 5.8026. Min Act: -0.1700
Data Index: 1241347 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19