Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 628 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.3736. Min Act: -0.1700
Data Index: 8618971 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.2174. Min Act: -0.1700
Data Index: 4643154 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.1549. Min Act: -0.1700
Data Index: 1526931 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.0924. Min Act: -0.1700
Data Index: 4686250 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.0924. Min Act: -0.1700
Data Index: 7884443 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.0924. Min Act: -0.1700
Data Index: 5291248 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.0611. Min Act: -0.1700
Data Index: 1807875 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9986. Min Act: -0.1700
Data Index: 8681158 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3736. Min Range: -6.3736
Max Act: 6.0299. Min Act: -0.1700
Data Index: 1598930 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9986. Min Act: -0.1700
Data Index: 8805186 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9986. Min Act: -0.1700
Data Index: 4627994 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9986. Min Act: -0.1700
Data Index: 5070581 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9674. Min Act: -0.1700
Data Index: 5157435 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9361. Min Act: -0.1700
Data Index: 779111 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9049. Min Act: -0.1700
Data Index: 6165906 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9674. Min Act: -0.1700
Data Index: 558829 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9361. Min Act: -0.1700
Data Index: 2295231 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9049. Min Act: -0.1700
Data Index: 7553952 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9049. Min Act: -0.1700
Data Index: 1282655 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3736. Min Range: -6.3736
Max Act: 5.9361. Min Act: -0.1700
Data Index: 5717436 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19