Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5009 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.4236. Min Act: -0.1700
Data Index: 7980798 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.3924. Min Act: -0.1700
Data Index: 8470053 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.3299. Min Act: -0.1699
Data Index: 3339911 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.3924. Min Act: -0.1700
Data Index: 7283586 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.3299. Min Act: -0.1700
Data Index: 920899 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.3611. Min Act: -0.1700
Data Index: 663847 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.3299. Min Act: -0.1690
Data Index: 2069159 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2674. Min Act: -0.1700
Data Index: 1996553 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2986. Min Act: -0.1700
Data Index: 2314336 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2674. Min Act: -0.1700
Data Index: 4291438 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2674. Min Act: -0.1699
Data Index: 1983465 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2361. Min Act: -0.1700
Data Index: 3236879 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2674. Min Act: -0.1700
Data Index: 4033009 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2674. Min Act: -0.1700
Data Index: 7980793 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2361. Min Act: -0.1700
Data Index: 6943024 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2361. Min Act: -0.1700
Data Index: 45502 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2361. Min Act: -0.1700
Data Index: 8222098 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2048. Min Act: -0.1700
Data Index: 4121938 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2048. Min Act: -0.1700
Data Index: 4325920 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4236. Min Range: -4.4236
Max Act: 4.2048. Min Act: -0.1700
Data Index: 8111740 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19