Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6919. Min Act: -0.1700
Data Index: 1645092 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6759. Min Act: -0.1700
Data Index: 3305669 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6919. Min Act: -0.1700
Data Index: 4734581 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6598. Min Act: -0.1700
Data Index: 7760008 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6759. Min Act: -0.1700
Data Index: 4872483 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6759. Min Act: -0.1700
Data Index: 258026 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6438. Min Act: -0.1700
Data Index: 8562872 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6438. Min Act: -0.1700
Data Index: 8749375 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6598. Min Act: -0.1700
Data Index: 6607652 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6277. Min Act: -0.1700
Data Index: 3470189 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6117. Min Act: -0.1700
Data Index: 1136016 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6117. Min Act: -0.1700
Data Index: 8192017 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6438. Min Act: -0.1700
Data Index: 1059215 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6277. Min Act: -0.1700
Data Index: 3278678 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6438. Min Act: -0.1700
Data Index: 6823431 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6117. Min Act: -0.1700
Data Index: 6292071 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.6117. Min Act: -0.1700
Data Index: 3920190 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.5956. Min Act: -0.1700
Data Index: 5071772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.5956. Min Act: -0.1700
Data Index: 2793096 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6919. Min Range: -2.6919
Max Act: 2.5633. Min Act: -0.1700
Data Index: 1141178 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19