Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 6071568 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 3273156 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1405. Min Act: -0.1700
Data Index: 3976264 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1248. Min Act: -0.1700
Data Index: 5073830 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0932. Min Act: -0.1700
Data Index: 8077460 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1090. Min Act: -0.1700
Data Index: 2723634 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 2497904 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0775. Min Act: -0.1700
Data Index: 4201239 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0775. Min Act: -0.1700
Data Index: 3252332 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0617. Min Act: -0.1700
Data Index: 4972384 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 7143853 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0617. Min Act: -0.1700
Data Index: 4241827 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 7194084 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 3530214 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 7163664 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 5467779 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 2247162 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 3626005 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 3111098 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 5028766 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19