Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.6285. Min Act: -0.1700
Data Index: 503710 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.5973. Min Act: -0.1700
Data Index: 2914435 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.5660. Min Act: -0.1700
Data Index: 2379203 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.5035. Min Act: -0.1700
Data Index: 7384301 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.5035. Min Act: -0.1700
Data Index: 839896 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.4410. Min Act: -0.1700
Data Index: 665947 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.4098. Min Act: -0.1700
Data Index: 100259 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.4098. Min Act: -0.1700
Data Index: 3794831 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.4410. Min Act: -0.1700
Data Index: 2333740 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.4098. Min Act: -0.1700
Data Index: 6036334 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3473. Min Act: -0.1700
Data Index: 8714131 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3473. Min Act: -0.1700
Data Index: 1305579 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3473. Min Act: -0.1700
Data Index: 8165535 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3473. Min Act: -0.1700
Data Index: 1480556 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3473. Min Act: -0.1700
Data Index: 7010947 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3160. Min Act: -0.1700
Data Index: 2422952 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3160. Min Act: -0.1700
Data Index: 4602241 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1045520 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.2848. Min Act: -0.1700
Data Index: 6845550 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6285. Min Range: -4.6285
Max Act: 4.3160. Min Act: -0.1700
Data Index: 5130778 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19