Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6334 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.0258. Min Range: -16.0258
Max Act: 16.0258. Min Act: -0.1699
Data Index: 7144022 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.0258. Min Range: -16.0258
Max Act: 15.0258. Min Act: -0.1700
Data Index: 2655351 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.9633. Min Act: -0.1700
Data Index: 3732255 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.7758. Min Act: -0.1700
Data Index: 6143093 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.9008. Min Act: -0.1700
Data Index: 4754298 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.6508. Min Act: -0.1699
Data Index: 528616 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.6508. Min Act: -0.1700
Data Index: 3413981 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.5883. Min Act: -0.1700
Data Index: 2135596 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.5883. Min Act: -0.1700
Data Index: 1454107 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.6508. Min Act: -0.1700
Data Index: 41356 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.5258. Min Act: -0.1699
Data Index: 4754284 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.4633. Min Act: -0.1700
Data Index: 4324271 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.5258. Min Act: -0.1700
Data Index: 4460255 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.4008. Min Act: -0.1699
Data Index: 7355211 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.3383. Min Act: -0.1700
Data Index: 249275 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.2133. Min Act: -0.1699
Data Index: 4957196 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.1508. Min Act: -0.1700
Data Index: 4492407 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.0258. Min Act: -0.1700
Data Index: 3884834 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.0258. Min Range: -16.0258
Max Act: 14.0258. Min Act: -0.1700
Data Index: 4141066 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.0258. Min Range: -16.0258
Max Act: 13.9633. Min Act: -0.1700
Data Index: 3357537 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19