Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 233 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2848. Min Act: -0.1700
Data Index: 5018754 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2353. Min Act: -0.1700
Data Index: 4598774 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2353. Min Act: -0.1700
Data Index: 5018753 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2187. Min Act: -0.1700
Data Index: 8411734 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2187. Min Act: -0.1700
Data Index: 258824 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2021. Min Act: -0.1700
Data Index: 5018752 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2021. Min Act: -0.1700
Data Index: 2173456 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1855. Min Act: -0.1700
Data Index: 3819543 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.2021. Min Act: -0.1700
Data Index: 2381999 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1855. Min Act: -0.1700
Data Index: 5951769 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 7403175 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 6664588 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 4544532 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 5228427 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1522. Min Act: -0.1700
Data Index: 893143 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 1362640 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 7002993 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 354533 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1522. Min Act: -0.1700
Data Index: 7417336 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2848. Min Range: -2.2848
Max Act: 2.1689. Min Act: -0.1700
Data Index: 5212948 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19