Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1842 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0632. Min Range: -7.0632
Max Act: 7.0632. Min Act: -0.1700
Data Index: 1931093 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.9694. Min Act: -0.1700
Data Index: 2476295 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.9694. Min Act: -0.1700
Data Index: 5474754 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.9069. Min Act: -0.1700
Data Index: 7138889 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.8444. Min Act: -0.1700
Data Index: 3233670 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.8444. Min Act: -0.1700
Data Index: 2046320 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.8132. Min Act: -0.1700
Data Index: 6131832 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.7819. Min Act: -0.1700
Data Index: 7268984 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.8132. Min Act: -0.1700
Data Index: 950151 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.7819. Min Act: -0.1700
Data Index: 346909 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.7507. Min Act: -0.1700
Data Index: 1248043 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.7194. Min Act: -0.1700
Data Index: 6396072 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.7194. Min Act: -0.1700
Data Index: 6005900 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.6257. Min Act: -0.1700
Data Index: 5757093 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.5944. Min Act: -0.1700
Data Index: 426637 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.6257. Min Act: -0.1700
Data Index: 5062050 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.6257. Min Act: -0.1700
Data Index: 8030649 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.5944. Min Act: -0.1700
Data Index: 8268225 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.5944. Min Act: -0.1700
Data Index: 1415403 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0632. Min Range: -7.0632
Max Act: 6.5944. Min Act: -0.1700
Data Index: 6341878 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19