Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4198 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2996. Min Range: -5.2996
Max Act: 5.2996. Min Act: -0.1700
Data Index: 408367 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2996. Min Range: -5.2996
Max Act: 5.0183. Min Act: -0.1700
Data Index: 8296383 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.8933. Min Act: -0.1700
Data Index: 5474771 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.8308. Min Act: -0.1700
Data Index: 8764266 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.8308. Min Act: -0.1700
Data Index: 8411604 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7996. Min Act: -0.1700
Data Index: 8671420 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7683. Min Act: -0.1700
Data Index: 2607414 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7996. Min Act: -0.1700
Data Index: 2649238 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7683. Min Act: -0.1700
Data Index: 498321 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7683. Min Act: -0.1700
Data Index: 7762325 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7683. Min Act: -0.1700
Data Index: 5780831 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6746. Min Act: -0.1700
Data Index: 6700115 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.7371. Min Act: -0.1700
Data Index: 5858164 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6746. Min Act: -0.1700
Data Index: 8528902 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6746. Min Act: -0.1700
Data Index: 2035731 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6433. Min Act: -0.1700
Data Index: 4943454 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6433. Min Act: -0.1700
Data Index: 706195 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6433. Min Act: -0.1700
Data Index: 3394016 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6121. Min Act: -0.1700
Data Index: 2931481 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2996. Min Range: -5.2996
Max Act: 4.6121. Min Act: -0.1700
Data Index: 523063 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19