Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1610 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6949. Min Range: -7.6949
Max Act: 7.6949. Min Act: -0.1700
Data Index: 5933232 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6949. Min Range: -7.6949
Max Act: 7.2887. Min Act: -0.1700
Data Index: 2289300 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6949. Min Range: -7.6949
Max Act: 7.2262. Min Act: -0.1700
Data Index: 3533373 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6949. Min Range: -7.6949
Max Act: 7.0074. Min Act: -0.1700
Data Index: 1937739 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.9449. Min Act: -0.1700
Data Index: 2552683 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.9137. Min Act: -0.1700
Data Index: 5336984 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.9137. Min Act: -0.1700
Data Index: 2485239 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.9137. Min Act: -0.1700
Data Index: 5279806 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.8824. Min Act: -0.1700
Data Index: 7269299 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.8824. Min Act: -0.1700
Data Index: 8089905 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.8824. Min Act: -0.1700
Data Index: 3688820 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.8199. Min Act: -0.1700
Data Index: 3380959 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.7887. Min Act: -0.1700
Data Index: 7666746 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.7574. Min Act: -0.1700
Data Index: 5916538 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.7887. Min Act: -0.1700
Data Index: 2525586 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.7574. Min Act: -0.1700
Data Index: 3822226 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.7262. Min Act: -0.1700
Data Index: 7028438 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.6637. Min Act: -0.1700
Data Index: 8086451 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.6949. Min Act: -0.1700
Data Index: 7942658 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6949. Min Range: -7.6949
Max Act: 6.6949. Min Act: -0.1700
Data Index: 1455915 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19