Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2903. Min Range: -7.2903
Max Act: 7.2903. Min Act: -0.1700
Data Index: 8784429 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2903. Min Range: -7.2903
Max Act: 7.1653. Min Act: -0.1700
Data Index: 7079456 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2903. Min Range: -7.2903
Max Act: 7.0403. Min Act: -0.1700
Data Index: 2103425 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.9778. Min Act: -0.1700
Data Index: 6710862 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.9778. Min Act: -0.1700
Data Index: 8181250 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.9466. Min Act: -0.1700
Data Index: 5946107 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.9153. Min Act: -0.1700
Data Index: 8433130 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.8841. Min Act: -0.1700
Data Index: 7061736 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.8528. Min Act: -0.1700
Data Index: 5164124 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.8528. Min Act: -0.1700
Data Index: 62318 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 8511989 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 14557 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 6543991 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 5421547 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 3828717 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 2811563 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 8634088 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7278. Min Act: -0.1700
Data Index: 3530240 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7278. Min Act: -0.1700
Data Index: 7184555 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2903. Min Range: -7.2903
Max Act: 6.7591. Min Act: -0.1700
Data Index: 8543258 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19