Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4600 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0092. Min Range: -7.0092
Max Act: 7.0092. Min Act: -0.1700
Data Index: 1948814 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.9780. Min Act: -0.1700
Data Index: 8568299 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.9780. Min Act: -0.1700
Data Index: 5459717 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.7280. Min Act: -0.1700
Data Index: 805307 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.6030. Min Act: -0.1700
Data Index: 6546347 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.6030. Min Act: -0.1700
Data Index: 7348383 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.3217. Min Act: -0.1700
Data Index: 1955563 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.2592. Min Act: -0.1700
Data Index: 4833889 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.2905. Min Act: -0.1700
Data Index: 5366400 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.2592. Min Act: -0.1700
Data Index: 1158457 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.2592. Min Act: -0.1700
Data Index: 4873897 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.2280. Min Act: -0.1700
Data Index: 4777619 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1655. Min Act: -0.1700
Data Index: 8697503 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1655. Min Act: -0.1700
Data Index: 636712 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1655. Min Act: -0.1700
Data Index: 3070382 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1342. Min Act: -0.1700
Data Index: 3190729 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1342. Min Act: -0.1700
Data Index: 3990776 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1030. Min Act: -0.1700
Data Index: 2628079 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1030. Min Act: -0.1700
Data Index: 3027266 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0092. Min Range: -7.0092
Max Act: 6.1030. Min Act: -0.1700
Data Index: 7487363 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19