Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.9159. Min Act: -0.1700
Data Index: 5589772 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.6034. Min Act: -0.1700
Data Index: 2787260 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.6034. Min Act: -0.1700
Data Index: 5175553 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.5409. Min Act: -0.1700
Data Index: 4226699 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.5409. Min Act: -0.1700
Data Index: 6286601 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4784. Min Act: -0.1700
Data Index: 4041757 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.5409. Min Act: -0.1700
Data Index: 3347833 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4784. Min Act: -0.1700
Data Index: 7927279 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4159. Min Act: -0.1700
Data Index: 7349957 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4784. Min Act: -0.1700
Data Index: 5671554 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4784. Min Act: -0.1700
Data Index: 1849238 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4159. Min Act: -0.1700
Data Index: 2817175 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4159. Min Act: -0.1700
Data Index: 414216 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4159. Min Act: -0.1700
Data Index: 4987896 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.4159. Min Act: -0.1700
Data Index: 4445725 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.2909. Min Act: -0.1700
Data Index: 5386572 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.3534. Min Act: -0.1700
Data Index: 733381 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.3534. Min Act: -0.1700
Data Index: 3360277 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.3534. Min Act: -0.1700
Data Index: 2323558 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9159. Min Range: -8.9159
Max Act: 8.3534. Min Act: -0.1700
Data Index: 3017379 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19