Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.8900. Min Act: -0.1700
Data Index: 2382395 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.8275. Min Act: -0.1700
Data Index: 3401985 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.8275. Min Act: -0.1700
Data Index: 3401987 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.7649. Min Act: -0.1700
Data Index: 7450932 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.8275. Min Act: -0.1700
Data Index: 2996399 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.7337. Min Act: -0.1700
Data Index: 4451556 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.7024. Min Act: -0.1700
Data Index: 2701077 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.6085. Min Act: -0.1700
Data Index: 8797920 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.6398. Min Act: -0.1700
Data Index: 3251735 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5772. Min Act: -0.1700
Data Index: 6719207 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.6085. Min Act: -0.1700
Data Index: 6548791 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5459. Min Act: -0.1700
Data Index: 4225358 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.6085. Min Act: -0.1700
Data Index: 5349109 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.6085. Min Act: -0.1700
Data Index: 5560547 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5772. Min Act: -0.1700
Data Index: 2508393 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5772. Min Act: -0.1700
Data Index: 7040471 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5302. Min Act: -0.1700
Data Index: 2641723 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5772. Min Act: -0.1700
Data Index: 699171 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5772. Min Act: -0.1700
Data Index: 2548740 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8900. Min Range: -3.8900
Max Act: 3.5772. Min Act: -0.1700
Data Index: 3191365 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19