Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 804266 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6855734 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3747. Min Act: -0.1700
Data Index: 8278089 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3747. Min Act: -0.1700
Data Index: 5313006 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3122. Min Act: -0.1700
Data Index: 8010336 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2810. Min Act: -0.1700
Data Index: 8315036 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 1225200 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 3700474 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2185. Min Act: -0.1700
Data Index: 2909827 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 257177 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1560. Min Act: -0.1700
Data Index: 6467486 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 3273376 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 6143412 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1560. Min Act: -0.1700
Data Index: 6926556 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1560. Min Act: -0.1700
Data Index: 2345775 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.0935. Min Act: -0.1700
Data Index: 7550447 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1247. Min Act: -0.1700
Data Index: 6544580 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1247. Min Act: -0.1700
Data Index: 5859590 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.0935. Min Act: -0.1700
Data Index: 3144851 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.0935. Min Act: -0.1700
Data Index: 7433028 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19