Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.7893. Min Act: -0.1700
Data Index: 7456493 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.7580. Min Act: -0.1700
Data Index: 2347135 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.7580. Min Act: -0.1700
Data Index: 489893 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.7268. Min Act: -0.1700
Data Index: 6906618 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.5393. Min Act: -0.1700
Data Index: 8354709 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.6018. Min Act: -0.1700
Data Index: 4631802 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.5393. Min Act: -0.1700
Data Index: 496353 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.5393. Min Act: -0.1700
Data Index: 306567 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.5080. Min Act: -0.1700
Data Index: 6284966 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.5080. Min Act: -0.1700
Data Index: 8775050 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.4768. Min Act: -0.1700
Data Index: 1922045 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.4143. Min Act: -0.1700
Data Index: 8225938 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.4143. Min Act: -0.1700
Data Index: 5647344 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.4143. Min Act: -0.1700
Data Index: 5394234 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.3830. Min Act: -0.1700
Data Index: 1771648 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.3205. Min Act: -0.1700
Data Index: 2085204 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.3518. Min Act: -0.1700
Data Index: 4309771 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.2893. Min Act: -0.1700
Data Index: 1367742 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.3205. Min Act: -0.1700
Data Index: 2323917 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7893. Min Range: -6.7893
Max Act: 6.3205. Min Act: -0.1700
Data Index: 4125779 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19