Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3999. Min Act: -0.1700
Data Index: 2717132 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3509. Min Act: -0.1700
Data Index: 7353119 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3509. Min Act: -0.1700
Data Index: 1001371 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3181. Min Act: -0.1700
Data Index: 1417914 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3181. Min Act: -0.1700
Data Index: 7026946 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3016. Min Act: -0.1700
Data Index: 2665352 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.3016. Min Act: -0.1700
Data Index: 3223917 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2852. Min Act: -0.1700
Data Index: 2114969 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2852. Min Act: -0.1700
Data Index: 4431970 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2852. Min Act: -0.1700
Data Index: 3391514 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2852. Min Act: -0.1700
Data Index: 5348730 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2687. Min Act: -0.1700
Data Index: 3860195 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2687. Min Act: -0.1700
Data Index: 5929510 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2687. Min Act: -0.1700
Data Index: 2178320 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2687. Min Act: -0.1700
Data Index: 227273 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2687. Min Act: -0.1700
Data Index: 4057370 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2522. Min Act: -0.1700
Data Index: 2655934 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2191. Min Act: -0.1700
Data Index: 1917510 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2522. Min Act: -0.1700
Data Index: 26789 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3999. Min Range: -2.3999
Max Act: 2.2191. Min Act: -0.1700
Data Index: 5628865 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19