Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0993. Min Act: -0.1700
Data Index: 3537579 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0993. Min Range: -6.0993
Max Act: 6.0993. Min Act: -0.1700
Data Index: 6892745 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9431. Min Act: -0.1700
Data Index: 5265343 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9431. Min Act: -0.1700
Data Index: 4521777 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.9431. Min Act: -0.1700
Data Index: 4587419 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8806. Min Act: -0.1700
Data Index: 1062383 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8806. Min Act: -0.1700
Data Index: 5234310 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6770892 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.8493. Min Act: -0.1700
Data Index: 8299557 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.7868. Min Act: -0.1700
Data Index: 5992441 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.7868. Min Act: -0.1700
Data Index: 8751766 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.7556. Min Act: -0.1700
Data Index: 5508288 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.7556. Min Act: -0.1700
Data Index: 5153272 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.6931. Min Act: -0.1700
Data Index: 396977 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.6931. Min Act: -0.1700
Data Index: 7928438 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.6931. Min Act: -0.1700
Data Index: 6640867 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.6931. Min Act: -0.1700
Data Index: 5030509 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.7243. Min Act: -0.1700
Data Index: 3904981 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.6618. Min Act: -0.1700
Data Index: 733578 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0993. Min Range: -6.0993
Max Act: 5.6306. Min Act: -0.1700
Data Index: 149987 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19