Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.3823. Min Act: -0.1700
Data Index: 8516251 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1948. Min Act: -0.1700
Data Index: 3849099 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1948. Min Act: -0.1700
Data Index: 3023241 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1323. Min Act: -0.1700
Data Index: 8156633 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1948. Min Act: -0.1700
Data Index: 3208602 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1323. Min Act: -0.1700
Data Index: 5334665 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1323. Min Act: -0.1700
Data Index: 1332140 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1323. Min Act: -0.1700
Data Index: 7120953 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1011. Min Act: -0.1700
Data Index: 6685630 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1011. Min Act: -0.1700
Data Index: 2786535 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.1011. Min Act: -0.1700
Data Index: 1507885 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0698. Min Act: -0.1699
Data Index: 8484211 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0386. Min Act: -0.1700
Data Index: 3936118 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0698. Min Act: -0.1700
Data Index: 267764 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0698. Min Act: -0.1700
Data Index: 3438218 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0698. Min Act: -0.1700
Data Index: 3704786 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0073. Min Act: -0.1700
Data Index: 5835639 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0698. Min Act: -0.1700
Data Index: 3014793 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0386. Min Act: -0.1700
Data Index: 84879 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3823. Min Range: -5.3823
Max Act: 5.0386. Min Act: -0.1700
Data Index: 4455005 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19