Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4834. Min Range: -5.4834
Max Act: 5.4834. Min Act: -0.1700
Data Index: 7562 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4834. Min Range: -5.4834
Max Act: 5.2334. Min Act: -0.1700
Data Index: 2249179 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4834. Min Range: -5.4834
Max Act: 5.2022. Min Act: -0.1699
Data Index: 7779939 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4834. Min Range: -5.4834
Max Act: 5.1397. Min Act: -0.1700
Data Index: 179274 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4834. Min Range: -5.4834
Max Act: 5.2022. Min Act: -0.1700
Data Index: 8406966 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.7959. Min Act: -0.1700
Data Index: 6766228 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.8272. Min Act: -0.1700
Data Index: 2333090 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.8272. Min Act: -0.1700
Data Index: 3034599 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.7022. Min Act: -0.1700
Data Index: 7287380 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.5772. Min Act: -0.1700
Data Index: 4095130 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.6084. Min Act: -0.1700
Data Index: 6572219 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.7022. Min Act: -0.1700
Data Index: 4328431 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.5772. Min Act: -0.1698
Data Index: 4478297 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.5459. Min Act: -0.1700
Data Index: 4112683 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.3897. Min Act: -0.1700
Data Index: 6516582 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.3584. Min Act: -0.1700
Data Index: 6336968 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.2959. Min Act: -0.1700
Data Index: 5537037 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.3272. Min Act: -0.1700
Data Index: 4095124 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.1397. Min Act: -0.1700
Data Index: 4252658 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4834. Min Range: -5.4834
Max Act: 4.2334. Min Act: -0.1700
Data Index: 5807278 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19