Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6044 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.6907. Min Act: -0.1700
Data Index: 7142927 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.6907. Min Act: -0.1700
Data Index: 5658813 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.6282. Min Act: -0.1700
Data Index: 5828661 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.5970. Min Act: -0.1700
Data Index: 6030447 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2384881 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5956267 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.4095. Min Act: -0.1700
Data Index: 2182219 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3782. Min Act: -0.1700
Data Index: 6399188 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3782. Min Act: -0.1700
Data Index: 7406422 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3470. Min Act: -0.1700
Data Index: 6639923 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3470. Min Act: -0.1700
Data Index: 3969799 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.2845. Min Act: -0.1700
Data Index: 583123 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3470. Min Act: -0.1700
Data Index: 5343225 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3157. Min Act: -0.1700
Data Index: 6717871 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3157. Min Act: -0.1700
Data Index: 5157888 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3157. Min Act: -0.1700
Data Index: 5790310 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.3157. Min Act: -0.1700
Data Index: 163674 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.2845. Min Act: -0.1700
Data Index: 1773873 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.2845. Min Act: -0.1700
Data Index: 1235646 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6907. Min Range: -5.6907
Max Act: 5.2532. Min Act: -0.1700
Data Index: 4381868 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19