Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.5166. Min Range: -10.5166
Max Act: 10.5166. Min Act: -0.1700
Data Index: 5219315 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5166. Min Range: -10.5166
Max Act: 10.3291. Min Act: -0.1700
Data Index: 8185141 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5166. Min Range: -10.5166
Max Act: 10.2666. Min Act: -0.1700
Data Index: 333062 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5166. Min Range: -10.5166
Max Act: 10.1416. Min Act: -0.1700
Data Index: 6716782 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.9541. Min Act: -0.1700
Data Index: 7802684 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.8916. Min Act: -0.1700
Data Index: 8832362 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.8291. Min Act: -0.1700
Data Index: 8538215 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.8291. Min Act: -0.1700
Data Index: 433079 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.8291. Min Act: -0.1700
Data Index: 4870238 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.8291. Min Act: -0.1700
Data Index: 7396246 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.7041. Min Act: -0.1700
Data Index: 5580558 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.7041. Min Act: -0.1700
Data Index: 6577553 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.7041. Min Act: -0.1700
Data Index: 8085180 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.7041. Min Act: -0.1700
Data Index: 6242578 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.6416. Min Act: -0.1700
Data Index: 4935267 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.6416. Min Act: -0.1700
Data Index: 299299 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.7041. Min Act: -0.1700
Data Index: 2234273 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.6416. Min Act: -0.1700
Data Index: 3482152 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.6416. Min Act: -0.1700
Data Index: 3895907 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5166. Min Range: -10.5166
Max Act: 9.6416. Min Act: -0.1700
Data Index: 2539647 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19