Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0125. Min Range: -2.0125
Max Act: 2.0125. Min Act: -0.1700
Data Index: 5152605 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9617. Min Act: -0.1700
Data Index: 1074988 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9617. Min Act: -0.1700
Data Index: 8082186 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9278. Min Act: -0.1700
Data Index: 5633637 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9278. Min Act: -0.1700
Data Index: 3536603 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9278. Min Act: -0.1700
Data Index: 7091921 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9278. Min Act: -0.1700
Data Index: 4770217 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9107. Min Act: -0.1700
Data Index: 7983163 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 6247987 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9107. Min Act: -0.1700
Data Index: 7643541 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9107. Min Act: -0.1700
Data Index: 5751274 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9107. Min Act: -0.1700
Data Index: 7774305 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.9107. Min Act: -0.1700
Data Index: 7942016 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8766. Min Act: -0.1700
Data Index: 1607132 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 4562355 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 7787603 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 310128 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 3838605 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 5315739 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0125. Min Range: -2.0125
Max Act: 1.8937. Min Act: -0.1700
Data Index: 949222 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19