Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.3853. Min Act: -0.1700
Data Index: 3581283 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.2916. Min Act: -0.1700
Data Index: 2914907 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.1978. Min Act: -0.1700
Data Index: 5406513 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.2291. Min Act: -0.1700
Data Index: 6205653 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.1353. Min Act: -0.1700
Data Index: 4772144 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0728. Min Act: -0.1700
Data Index: 4151626 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.1041. Min Act: -0.1700
Data Index: 3095226 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0416. Min Act: -0.1700
Data Index: 7028231 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0416. Min Act: -0.1700
Data Index: 1257281 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0416. Min Act: -0.1700
Data Index: 1120138 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0728. Min Act: -0.1700
Data Index: 402377 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0103. Min Act: -0.1700
Data Index: 1185025 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0103. Min Act: -0.1700
Data Index: 4863417 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0103. Min Act: -0.1700
Data Index: 8106118 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0103. Min Act: -0.1700
Data Index: 1369350 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3853. Min Range: -6.3853
Max Act: 5.9478. Min Act: -0.1700
Data Index: 3442968 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3853. Min Range: -6.3853
Max Act: 6.0103. Min Act: -0.1700
Data Index: 2060399 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3853. Min Range: -6.3853
Max Act: 5.9791. Min Act: -0.1700
Data Index: 8103346 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3853. Min Range: -6.3853
Max Act: 5.9166. Min Act: -0.1700
Data Index: 1840071 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3853. Min Range: -6.3853
Max Act: 5.9478. Min Act: -0.1700
Data Index: 6126157 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19