Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.6019. Min Act: -0.1700
Data Index: 1122365 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.5394. Min Act: -0.1700
Data Index: 4521235 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.5394. Min Act: -0.1700
Data Index: 8337769 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.3519. Min Act: -0.1700
Data Index: 5907418 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.2269. Min Act: -0.1700
Data Index: 3737520 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.2269. Min Act: -0.1700
Data Index: 2594435 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1644. Min Act: -0.1700
Data Index: 1074358 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.2269. Min Act: -0.1700
Data Index: 7261955 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.2269. Min Act: -0.1700
Data Index: 731770 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1644. Min Act: -0.1700
Data Index: 403020 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1644. Min Act: -0.1700
Data Index: 8397905 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 2211839 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1644. Min Act: -0.1700
Data Index: 7150206 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1644. Min Act: -0.1700
Data Index: 6799252 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6309940 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 2144127 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 4571904 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6511544 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6494885 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6019. Min Range: -8.6019
Max Act: 8.0394. Min Act: -0.1700
Data Index: 5040725 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19