Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0194. Min Range: -5.0194
Max Act: 5.0194. Min Act: -0.1700
Data Index: 3054281 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.9569. Min Act: -0.1700
Data Index: 3054282 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.8007. Min Act: -0.1700
Data Index: 1636513 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.7694. Min Act: -0.1700
Data Index: 1532040 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.7382. Min Act: -0.1700
Data Index: 7462190 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.7382. Min Act: -0.1700
Data Index: 7681292 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.7069. Min Act: -0.1700
Data Index: 3051678 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6757. Min Act: -0.1700
Data Index: 3764462 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6757. Min Act: -0.1700
Data Index: 7674781 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6757. Min Act: -0.1700
Data Index: 6126614 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6757. Min Act: -0.1700
Data Index: 6401957 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6132. Min Act: -0.1700
Data Index: 5148566 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6444. Min Act: -0.1700
Data Index: 2351527 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6444. Min Act: -0.1700
Data Index: 1480761 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6444. Min Act: -0.1700
Data Index: 1167968 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6444. Min Act: -0.1700
Data Index: 8018330 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.6444. Min Act: -0.1700
Data Index: 8784102 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5819. Min Act: -0.1700
Data Index: 7889484 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5819. Min Act: -0.1700
Data Index: 4609512 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0194. Min Range: -5.0194
Max Act: 4.5819. Min Act: -0.1700
Data Index: 4119010 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19