Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.7281. Min Act: -0.1700
Data Index: 6895833 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.6344. Min Act: -0.1700
Data Index: 7430250 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.5406. Min Act: -0.1700
Data Index: 5187108 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.5406. Min Act: -0.1700
Data Index: 3438341 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.5094. Min Act: -0.1700
Data Index: 1576567 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.5094. Min Act: -0.1700
Data Index: 7718017 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.5094. Min Act: -0.1700
Data Index: 6819213 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.4469. Min Act: -0.1700
Data Index: 2511598 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.4156. Min Act: -0.1700
Data Index: 6239349 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3844. Min Act: -0.1700
Data Index: 1953050 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3844. Min Act: -0.1700
Data Index: 3044050 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.4156. Min Act: -0.1700
Data Index: 7631219 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3531. Min Act: -0.1700
Data Index: 6305550 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3531. Min Act: -0.1700
Data Index: 4220862 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3531. Min Act: -0.1700
Data Index: 5359577 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3844. Min Act: -0.1700
Data Index: 3081860 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3531. Min Act: -0.1700
Data Index: 3438340 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3219. Min Act: -0.1700
Data Index: 779206 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3219. Min Act: -0.1700
Data Index: 6737947 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7281. Min Range: -5.7281
Max Act: 5.3219. Min Act: -0.1700
Data Index: 3001155 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19