Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4953. Min Act: -0.1700
Data Index: 975918 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4791. Min Act: -0.1700
Data Index: 314853 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4628. Min Act: -0.1700
Data Index: 8310826 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4791. Min Act: -0.1700
Data Index: 6155153 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4466. Min Act: -0.1700
Data Index: 1938889 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4466. Min Act: -0.1700
Data Index: 8085327 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4466. Min Act: -0.1700
Data Index: 5346519 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4466. Min Act: -0.1700
Data Index: 3486038 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4303. Min Act: -0.1700
Data Index: 8599309 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4466. Min Act: -0.1700
Data Index: 1102196 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4466. Min Act: -0.1700
Data Index: 121666 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4303. Min Act: -0.1700
Data Index: 3342156 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4303. Min Act: -0.1700
Data Index: 4277861 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4303. Min Act: -0.1700
Data Index: 5151403 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4303. Min Act: -0.1700
Data Index: 2112794 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4303. Min Act: -0.1700
Data Index: 8158167 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4140. Min Act: -0.1700
Data Index: 5551476 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.3977. Min Act: -0.1700
Data Index: 3894026 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4140. Min Act: -0.1700
Data Index: 7363728 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4953. Min Range: -2.4953
Max Act: 2.4140. Min Act: -0.1700
Data Index: 6696539 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19