Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.7194. Min Act: -0.1700
Data Index: 3174928 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5319. Min Act: -0.1700
Data Index: 93615 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5007. Min Act: -0.1700
Data Index: 8694008 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.5007. Min Act: -0.1700
Data Index: 7499259 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 197540 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4694. Min Act: -0.1700
Data Index: 4541737 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 2968895 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 7271406 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 5871797 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4069. Min Act: -0.1700
Data Index: 348364 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 8068933 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 3842598 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 693904 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 8005055 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 7644227 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4382. Min Act: -0.1700
Data Index: 388834 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4069. Min Act: -0.1700
Data Index: 3165144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4069. Min Act: -0.1700
Data Index: 5726513 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4069. Min Act: -0.1700
Data Index: 3165158 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7194. Min Range: -5.7194
Max Act: 5.4069. Min Act: -0.1700
Data Index: 1153944 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19