Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0196. Min Range: -3.0196
Max Act: 3.0196. Min Act: -0.1700
Data Index: 14681 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.9880. Min Act: -0.1700
Data Index: 4127492 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.9564. Min Act: -0.1700
Data Index: 8323322 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.8930. Min Act: -0.1700
Data Index: 538840 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.8771. Min Act: -0.1700
Data Index: 189150 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.8454. Min Act: -0.1700
Data Index: 1663900 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.8454. Min Act: -0.1700
Data Index: 2320450 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.8454. Min Act: -0.1700
Data Index: 8470508 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.8136. Min Act: -0.1700
Data Index: 1156522 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7976. Min Act: -0.1700
Data Index: 3710455 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7976. Min Act: -0.1700
Data Index: 5263117 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7817. Min Act: -0.1700
Data Index: 998082 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7817. Min Act: -0.1700
Data Index: 7509276 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7338. Min Act: -0.1700
Data Index: 5392880 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7498. Min Act: -0.1700
Data Index: 1897022 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7179. Min Act: -0.1700
Data Index: 2630821 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7338. Min Act: -0.1700
Data Index: 7610108 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7338. Min Act: -0.1700
Data Index: 2701311 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7179. Min Act: -0.1700
Data Index: 796700 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0196. Min Range: -3.0196
Max Act: 2.7179. Min Act: -0.1700
Data Index: 5615813 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19