Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2437 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.5668. Min Act: -0.1700
Data Index: 5281662 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.5981. Min Act: -0.1700
Data Index: 5809714 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.5511. Min Act: -0.1700
Data Index: 1329528 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.5042. Min Act: -0.1700
Data Index: 8161787 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.5198. Min Act: -0.1700
Data Index: 4262652 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4885. Min Act: -0.1700
Data Index: 19945 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4728. Min Act: -0.1700
Data Index: 6216854 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4572. Min Act: -0.1700
Data Index: 2904919 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4572. Min Act: -0.1700
Data Index: 6703997 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4572. Min Act: -0.1700
Data Index: 6039050 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4415. Min Act: -0.1700
Data Index: 1223385 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4415. Min Act: -0.1700
Data Index: 8161919 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4415. Min Act: -0.1700
Data Index: 964299 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4258. Min Act: -0.1700
Data Index: 3776725 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4415. Min Act: -0.1700
Data Index: 5899613 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.4258. Min Act: -0.1700
Data Index: 2084647 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.3945. Min Act: -0.1700
Data Index: 6475382 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.3945. Min Act: -0.1700
Data Index: 8585748 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.3945. Min Act: -0.1700
Data Index: 8167636 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5981. Min Range: -3.5981
Max Act: 3.3945. Min Act: -0.1700
Data Index: 7303369 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19