Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3380. Min Range: -6.3380
Max Act: 6.3380. Min Act: -0.1700
Data Index: 6758961 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3380. Min Range: -6.3380
Max Act: 6.2755. Min Act: -0.1700
Data Index: 8831030 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3380. Min Range: -6.3380
Max Act: 6.2443. Min Act: -0.1700
Data Index: 910277 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3380. Min Range: -6.3380
Max Act: 6.1193. Min Act: -0.1700
Data Index: 804290 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3380. Min Range: -6.3380
Max Act: 6.0255. Min Act: -0.1700
Data Index: 8221898 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9943. Min Act: -0.1700
Data Index: 2232855 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3380. Min Range: -6.3380
Max Act: 6.0255. Min Act: -0.1700
Data Index: 3872204 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9630. Min Act: -0.1700
Data Index: 3449999 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9630. Min Act: -0.1700
Data Index: 8441855 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9630. Min Act: -0.1700
Data Index: 2091118 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9630. Min Act: -0.1700
Data Index: 4917128 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9630. Min Act: -0.1700
Data Index: 2268875 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9318. Min Act: -0.1700
Data Index: 3628758 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9005. Min Act: -0.1700
Data Index: 5653166 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9318. Min Act: -0.1700
Data Index: 1639857 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9318. Min Act: -0.1700
Data Index: 1730190 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9005. Min Act: -0.1700
Data Index: 7747397 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9005. Min Act: -0.1700
Data Index: 7002264 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.9318. Min Act: -0.1700
Data Index: 6505190 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3380. Min Range: -6.3380
Max Act: 5.8693. Min Act: -0.1700
Data Index: 2428897 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19