Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.7038. Min Act: -0.1700
Data Index: 3418738 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.5629. Min Act: -0.1700
Data Index: 6270788 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.5473. Min Act: -0.1700
Data Index: 2454825 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.5160. Min Act: -0.1700
Data Index: 1992180 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.4376. Min Act: -0.1700
Data Index: 2454821 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3749. Min Act: -0.1700
Data Index: 4244124 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3436. Min Act: -0.1700
Data Index: 7002511 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3279. Min Act: -0.1700
Data Index: 6806519 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3436. Min Act: -0.1700
Data Index: 2509150 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3279. Min Act: -0.1700
Data Index: 8730049 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3279. Min Act: -0.1700
Data Index: 3164265 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3122. Min Act: -0.1700
Data Index: 1207698 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.2965. Min Act: -0.1700
Data Index: 5012525 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3279. Min Act: -0.1700
Data Index: 3554181 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3122. Min Act: -0.1700
Data Index: 970929 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3122. Min Act: -0.1700
Data Index: 7695560 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.3122. Min Act: -0.1700
Data Index: 1504829 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.2965. Min Act: -0.1700
Data Index: 8544541 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.2808. Min Act: -0.1700
Data Index: 1992174 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7038. Min Range: -3.7038
Max Act: 3.2494. Min Act: -0.1700
Data Index: 35183 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19