Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.4965. Min Act: -0.1700
Data Index: 6273479 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.4495. Min Act: -0.1700
Data Index: 3757566 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.4182. Min Act: -0.1700
Data Index: 3364162 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3712. Min Act: -0.1700
Data Index: 2365438 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3398. Min Act: -0.1700
Data Index: 8609684 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3241. Min Act: -0.1700
Data Index: 1008956 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3241. Min Act: -0.1700
Data Index: 1587283 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.3084. Min Act: -0.1700
Data Index: 8808589 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2927. Min Act: -0.1700
Data Index: 8762193 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2927. Min Act: -0.1700
Data Index: 4883153 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2770. Min Act: -0.1700
Data Index: 284961 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2770. Min Act: -0.1700
Data Index: 5594732 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2770. Min Act: -0.1700
Data Index: 4483549 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2613. Min Act: -0.1700
Data Index: 5643962 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2613. Min Act: -0.1700
Data Index: 870330 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2456. Min Act: -0.1700
Data Index: 6722587 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2613. Min Act: -0.1700
Data Index: 4704914 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2456. Min Act: -0.1700
Data Index: 4165934 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2456. Min Act: -0.1700
Data Index: 3249100 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4965. Min Range: -3.4965
Max Act: 3.2456. Min Act: -0.1700
Data Index: 1065647 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19