Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4957. Min Range: -7.4957
Max Act: 7.4957. Min Act: -0.1700
Data Index: 3096693 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4957. Min Range: -7.4957
Max Act: 7.2770. Min Act: -0.1700
Data Index: 6400609 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4957. Min Range: -7.4957
Max Act: 7.2145. Min Act: -0.1700
Data Index: 1099495 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4957. Min Range: -7.4957
Max Act: 7.0582. Min Act: -0.1700
Data Index: 4112383 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4957. Min Range: -7.4957
Max Act: 7.0270. Min Act: -0.1700
Data Index: 1588940 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.9645. Min Act: -0.1700
Data Index: 3789079 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4957. Min Range: -7.4957
Max Act: 7.0270. Min Act: -0.1700
Data Index: 8008530 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.9645. Min Act: -0.1700
Data Index: 3383519 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.9332. Min Act: -0.1700
Data Index: 5977342 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6316720 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8395. Min Act: -0.1700
Data Index: 528609 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8395. Min Act: -0.1700
Data Index: 1346176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8707. Min Act: -0.1700
Data Index: 5906936 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8082. Min Act: -0.1700
Data Index: 6971830 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7097850 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8082. Min Act: -0.1700
Data Index: 2067091 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8395. Min Act: -0.1700
Data Index: 5616974 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8082. Min Act: -0.1700
Data Index: 5817941 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.8082. Min Act: -0.1700
Data Index: 2885719 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4957. Min Range: -7.4957
Max Act: 6.7770. Min Act: -0.1700
Data Index: 8435540 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19