Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1457. Min Range: -6.1457
Max Act: 6.1457. Min Act: -0.1700
Data Index: 1387146 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.8644. Min Act: -0.1700
Data Index: 5355446 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.8644. Min Act: -0.1700
Data Index: 3688922 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.8332. Min Act: -0.1700
Data Index: 4026352 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.6457. Min Act: -0.1700
Data Index: 395750 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.6144. Min Act: -0.1700
Data Index: 7784036 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.5832. Min Act: -0.1700
Data Index: 4414353 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.5519. Min Act: -0.1700
Data Index: 4008049 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.5207. Min Act: -0.1700
Data Index: 8695049 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.4269. Min Act: -0.1700
Data Index: 8547914 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.4269. Min Act: -0.1700
Data Index: 2973743 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.3332. Min Act: -0.1700
Data Index: 2536433 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.3019. Min Act: -0.1700
Data Index: 6571778 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.2707. Min Act: -0.1700
Data Index: 6366107 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3073462 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.3019. Min Act: -0.1700
Data Index: 2144228 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.3019. Min Act: -0.1700
Data Index: 6075024 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.3019. Min Act: -0.1700
Data Index: 7311915 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.2707. Min Act: -0.1700
Data Index: 8129876 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1457. Min Range: -6.1457
Max Act: 5.2707. Min Act: -0.1700
Data Index: 5689628 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19