Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1039 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.6586. Min Act: -0.1700
Data Index: 2657134 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5336. Min Act: -0.1700
Data Index: 1047358 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5336. Min Act: -0.1700
Data Index: 2925985 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5649. Min Act: -0.1700
Data Index: 4221004 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5024. Min Act: -0.1700
Data Index: 5386246 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5024. Min Act: -0.1700
Data Index: 1470250 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5024. Min Act: -0.1700
Data Index: 3909959 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4711. Min Act: -0.1700
Data Index: 6733185 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.5024. Min Act: -0.1700
Data Index: 5903154 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4711. Min Act: -0.1700
Data Index: 6511364 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4399. Min Act: -0.1700
Data Index: 7018248 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4711. Min Act: -0.1700
Data Index: 563125 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4086. Min Act: -0.1700
Data Index: 3919912 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4086. Min Act: -0.1700
Data Index: 2984453 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4086. Min Act: -0.1700
Data Index: 4373967 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4086. Min Act: -0.1700
Data Index: 1021329 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.4086. Min Act: -0.1700
Data Index: 3712649 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.3774. Min Act: -0.1700
Data Index: 3120715 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.3774. Min Act: -0.1700
Data Index: 8361563 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6586. Min Range: -5.6586
Max Act: 5.3774. Min Act: -0.1700
Data Index: 2403087 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19