Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.3292. Min Act: -0.1700
Data Index: 1999158 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.2799. Min Act: -0.1700
Data Index: 6376490 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.2634. Min Act: -0.1700
Data Index: 4707315 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.2303. Min Act: -0.1700
Data Index: 7065209 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.2138. Min Act: -0.1700
Data Index: 4183226 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1972. Min Act: -0.1699
Data Index: 1507050 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1806. Min Act: -0.1700
Data Index: 2780375 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1806. Min Act: -0.1700
Data Index: 2215221 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1972. Min Act: -0.1700
Data Index: 2748819 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1639. Min Act: -0.1700
Data Index: 6514086 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1639. Min Act: -0.1700
Data Index: 726548 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1473. Min Act: -0.1700
Data Index: 385695 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1639. Min Act: -0.1700
Data Index: 6375525 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1473. Min Act: -0.1700
Data Index: 3785821 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1473. Min Act: -0.1700
Data Index: 6715210 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1473. Min Act: -0.1696
Data Index: 500662 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1306. Min Act: -0.1700
Data Index: 4718838 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1306. Min Act: -0.1700
Data Index: 4974328 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1306. Min Act: -0.1700
Data Index: 5760791 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3292. Min Range: -2.3292
Max Act: 2.1306. Min Act: -0.1700
Data Index: 6830330 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19