Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0307. Min Range: -4.0307
Max Act: 4.0307. Min Act: -0.1700
Data Index: 3896264 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.8744. Min Act: -0.1700
Data Index: 4483208 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.8431. Min Act: -0.1700
Data Index: 5264951 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.8118. Min Act: -0.1700
Data Index: 7268443 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7493. Min Act: -0.1700
Data Index: 1847187 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7336. Min Act: -0.1700
Data Index: 4068150 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7180. Min Act: -0.1700
Data Index: 4481225 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7180. Min Act: -0.1700
Data Index: 907201 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7023. Min Act: -0.1700
Data Index: 7158627 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7023. Min Act: -0.1700
Data Index: 109465 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.7180. Min Act: -0.1700
Data Index: 18532 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6711. Min Act: -0.1700
Data Index: 7274388 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6867. Min Act: -0.1700
Data Index: 6784508 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6867. Min Act: -0.1700
Data Index: 5421418 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6711. Min Act: -0.1700
Data Index: 8495020 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6554. Min Act: -0.1700
Data Index: 862864 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6711. Min Act: -0.1700
Data Index: 1061670 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6554. Min Act: -0.1700
Data Index: 7197379 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6398. Min Act: -0.1700
Data Index: 1225880 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0307. Min Range: -4.0307
Max Act: 3.6241. Min Act: -0.1700
Data Index: 2978205 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19