Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.5804. Min Act: -0.1700
Data Index: 6833503 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.5179. Min Act: -0.1700
Data Index: 7268447 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.4554. Min Act: -0.1700
Data Index: 370930 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.2054. Min Act: -0.1700
Data Index: 2584046 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.1429. Min Act: -0.1700
Data Index: 6433953 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.0491. Min Act: -0.1700
Data Index: 5252077 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5804. Min Range: -7.5804
Max Act: 7.0179. Min Act: -0.1700
Data Index: 6316406 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.9866. Min Act: -0.1700
Data Index: 3259309 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.9554. Min Act: -0.1700
Data Index: 5855125 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.9554. Min Act: -0.1700
Data Index: 5983216 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8929. Min Act: -0.1700
Data Index: 6908481 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8929. Min Act: -0.1700
Data Index: 4550035 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8929. Min Act: -0.1700
Data Index: 1733623 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 4748101 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8616. Min Act: -0.1700
Data Index: 5757348 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1691659 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8616. Min Act: -0.1700
Data Index: 7549529 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 5731683 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 2585325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5804. Min Range: -7.5804
Max Act: 6.8304. Min Act: -0.1700
Data Index: 6232582 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19