Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.4711. Min Act: -0.1700
Data Index: 3425541 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.4086. Min Act: -0.1700
Data Index: 4671160 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.3461. Min Act: -0.1700
Data Index: 1383016 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.3461. Min Act: -0.1700
Data Index: 8218033 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.3461. Min Act: -0.1700
Data Index: 1459731 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 3336877 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 3199346 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 3447141 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.1586. Min Act: -0.1700
Data Index: 2672942 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 7766858 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.1586. Min Act: -0.1700
Data Index: 7888847 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.1586. Min Act: -0.1700
Data Index: 2829297 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0961. Min Act: -0.1700
Data Index: 868190 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.1586. Min Act: -0.1700
Data Index: 4257579 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.2211. Min Act: -0.1700
Data Index: 1117381 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0961. Min Act: -0.1700
Data Index: 5353211 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0961. Min Act: -0.1700
Data Index: 2270991 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0961. Min Act: -0.1700
Data Index: 7543998 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4711. Min Range: -8.4711
Max Act: 8.0336. Min Act: -0.1700
Data Index: 2427149 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4711. Min Range: -8.4711
Max Act: 7.9711. Min Act: -0.1700
Data Index: 4808889 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19