Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1235 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0499. Min Range: -6.0499
Max Act: 6.0499. Min Act: -0.1700
Data Index: 6593586 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0499. Min Range: -6.0499
Max Act: 6.0187. Min Act: -0.1700
Data Index: 4477176 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.9874. Min Act: -0.1700
Data Index: 2197726 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.9874. Min Act: -0.1700
Data Index: 1333718 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8937. Min Act: -0.1700
Data Index: 3715260 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.9249. Min Act: -0.1700
Data Index: 1630544 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.9249. Min Act: -0.1700
Data Index: 4834553 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8937. Min Act: -0.1700
Data Index: 7159612 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8937. Min Act: -0.1700
Data Index: 3295810 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4913998 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8937. Min Act: -0.1700
Data Index: 8832358 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8624. Min Act: -0.1700
Data Index: 4283253 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8312. Min Act: -0.1700
Data Index: 7826246 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8312. Min Act: -0.1700
Data Index: 7567107 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8312. Min Act: -0.1700
Data Index: 2804924 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.7999. Min Act: -0.1700
Data Index: 929912 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8312. Min Act: -0.1700
Data Index: 829073 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.8312. Min Act: -0.1700
Data Index: 4083906 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.7999. Min Act: -0.1700
Data Index: 1236113 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0499. Min Range: -6.0499
Max Act: 5.7687. Min Act: -0.1700
Data Index: 6525496 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19