Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6322 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.7434. Min Act: -0.1700
Data Index: 7694275 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.7122. Min Act: -0.1700
Data Index: 7694276 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.6184. Min Act: -0.1700
Data Index: 7694274 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.5559. Min Act: -0.1700
Data Index: 1437727 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.5559. Min Act: -0.1700
Data Index: 7820053 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.5559. Min Act: -0.1700
Data Index: 7516243 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4934. Min Act: -0.1700
Data Index: 7334710 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4934. Min Act: -0.1700
Data Index: 2749056 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4622. Min Act: -0.1700
Data Index: 2239336 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4309. Min Act: -0.1700
Data Index: 2239337 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4309. Min Act: -0.1700
Data Index: 6098669 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4309. Min Act: -0.1700
Data Index: 7019339 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.4309. Min Act: -0.1700
Data Index: 495717 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3997. Min Act: -0.1700
Data Index: 7100208 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3997. Min Act: -0.1700
Data Index: 4273907 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3997. Min Act: -0.1700
Data Index: 176913 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3684. Min Act: -0.1700
Data Index: 6272412 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3684. Min Act: -0.1700
Data Index: 7525875 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3059. Min Act: -0.1700
Data Index: 1859190 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7434. Min Range: -5.7434
Max Act: 5.3059. Min Act: -0.1700
Data Index: 3053643 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19