Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.8568. Min Act: -0.1700
Data Index: 6907287 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.7630. Min Act: -0.1700
Data Index: 2096935 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.7160. Min Act: -0.1700
Data Index: 1048680 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.6535. Min Act: -0.1700
Data Index: 1052310 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.6065. Min Act: -0.1700
Data Index: 1960745 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.5752. Min Act: -0.1700
Data Index: 3155994 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.5596. Min Act: -0.1700
Data Index: 5028135 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.5126. Min Act: -0.1700
Data Index: 2375037 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4969. Min Act: -0.1700
Data Index: 4160393 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.5282. Min Act: -0.1700
Data Index: 1699652 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4813. Min Act: -0.1700
Data Index: 3180958 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4813. Min Act: -0.1700
Data Index: 4160392 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4813. Min Act: -0.1700
Data Index: 7453720 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4656. Min Act: -0.1700
Data Index: 4177308 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4656. Min Act: -0.1700
Data Index: 6711911 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4499. Min Act: -0.1700
Data Index: 3104708 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4499. Min Act: -0.1700
Data Index: 4603618 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4656. Min Act: -0.1700
Data Index: 1049618 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4499. Min Act: -0.1700
Data Index: 1487279 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8568. Min Range: -3.8568
Max Act: 3.4499. Min Act: -0.1700
Data Index: 4950553 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19