Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.7268. Min Act: -0.1700
Data Index: 1893666 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.6331. Min Act: -0.1700
Data Index: 3105663 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.6331. Min Act: -0.1700
Data Index: 2495715 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.4768. Min Act: -0.1700
Data Index: 461194 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.4143. Min Act: -0.1700
Data Index: 644424 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.4456. Min Act: -0.1700
Data Index: 4727211 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.3831. Min Act: -0.1700
Data Index: 3091948 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.3206. Min Act: -0.1700
Data Index: 5356879 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.3206. Min Act: -0.1700
Data Index: 3179523 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.3206. Min Act: -0.1700
Data Index: 6788008 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2893. Min Act: -0.1700
Data Index: 3661303 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2893. Min Act: -0.1700
Data Index: 2655797 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2893. Min Act: -0.1700
Data Index: 7077729 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 4585473 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 3183550 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 3155341 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 7628893 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 6381492 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 8350095 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7268. Min Range: -7.7268
Max Act: 7.2581. Min Act: -0.1700
Data Index: 4621009 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19