Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.7277. Min Act: -0.1700
Data Index: 5138618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.6316. Min Act: -0.1700
Data Index: 4713383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5672. Min Act: -0.1700
Data Index: 7639115 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5188. Min Act: -0.1700
Data Index: 7761824 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5511. Min Act: -0.1700
Data Index: 6696125 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5349. Min Act: -0.1700
Data Index: 1428148 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5349. Min Act: -0.1700
Data Index: 1057891 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5349. Min Act: -0.1700
Data Index: 5825651 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5026. Min Act: -0.1700
Data Index: 6820914 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5188. Min Act: -0.1700
Data Index: 5014577 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5188. Min Act: -0.1700
Data Index: 7424004 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5188. Min Act: -0.1700
Data Index: 7104898 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5026. Min Act: -0.1700
Data Index: 588804 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.4864. Min Act: -0.1700
Data Index: 7557105 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5026. Min Act: -0.1700
Data Index: 2141891 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5026. Min Act: -0.1700
Data Index: 2131806 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5026. Min Act: -0.1700
Data Index: 4303326 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.4864. Min Act: -0.1700
Data Index: 4127400 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.4864. Min Act: -0.1700
Data Index: 3986450 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7277. Min Range: -2.7277
Max Act: 2.5188. Min Act: -0.1700
Data Index: 1542640 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19