Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.6713. Min Act: -0.1700
Data Index: 2539993 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.5151. Min Act: -0.1700
Data Index: 6343132 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3588. Min Act: -0.1700
Data Index: 1158268 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3588. Min Act: -0.1700
Data Index: 4407433 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3588. Min Act: -0.1700
Data Index: 4925217 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3588. Min Act: -0.1700
Data Index: 5558542 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3276. Min Act: -0.1700
Data Index: 3776161 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2963. Min Act: -0.1700
Data Index: 3587004 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2963. Min Act: -0.1700
Data Index: 437316 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2338. Min Act: -0.1700
Data Index: 5853743 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 3641658 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 1272146 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 7442320 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1088. Min Act: -0.1700
Data Index: 216045 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1401. Min Act: -0.1700
Data Index: 7485175 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1401. Min Act: -0.1700
Data Index: 3848939 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1401. Min Act: -0.1700
Data Index: 1346258 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1401. Min Act: -0.1700
Data Index: 2199938 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1088. Min Act: -0.1700
Data Index: 4448933 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1088. Min Act: -0.1700
Data Index: 115125 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19