Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.4443. Min Act: -0.1700
Data Index: 7193275 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.4443. Min Act: -0.1700
Data Index: 8769716 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.3818. Min Act: -0.1700
Data Index: 2013508 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.1943. Min Act: -0.1700
Data Index: 7811723 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.0693. Min Act: -0.1700
Data Index: 1307627 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.0068. Min Act: -0.1700
Data Index: 3255942 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.0068. Min Act: -0.1700
Data Index: 6434631 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.0068. Min Act: -0.1700
Data Index: 855886 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.9443. Min Act: -0.1700
Data Index: 5258807 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4443. Min Range: -8.4443
Max Act: 8.0068. Min Act: -0.1700
Data Index: 993984 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.9443. Min Act: -0.1700
Data Index: 6924229 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.9443. Min Act: -0.1700
Data Index: 3277918 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8818. Min Act: -0.1700
Data Index: 5282171 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8818. Min Act: -0.1700
Data Index: 6885640 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8818. Min Act: -0.1700
Data Index: 6296410 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8818. Min Act: -0.1700
Data Index: 2350897 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8193. Min Act: -0.1700
Data Index: 4746438 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8193. Min Act: -0.1700
Data Index: 4611956 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.7568. Min Act: -0.1700
Data Index: 2721758 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4443. Min Range: -8.4443
Max Act: 7.8193. Min Act: -0.1700
Data Index: 187531 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19