Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.7507. Min Act: -0.1700
Data Index: 4126883 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5945. Min Act: -0.1700
Data Index: 2830753 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5632. Min Act: -0.1700
Data Index: 7235825 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 1195253 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 436077 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 4479956 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 6629049 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 82852 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3132. Min Act: -0.1700
Data Index: 2608246 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 8485914 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3132. Min Act: -0.1700
Data Index: 4653782 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3132. Min Act: -0.1700
Data Index: 8403178 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 5025675 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 6900458 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 5841210 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 3257561 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 7473843 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2194. Min Act: -0.1700
Data Index: 7331238 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2194. Min Act: -0.1700
Data Index: 8296024 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2194. Min Act: -0.1700
Data Index: 1052346 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19