Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3070. Min Range: -7.3070
Max Act: 7.3070. Min Act: -0.1700
Data Index: 2317191 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3070. Min Range: -7.3070
Max Act: 7.1820. Min Act: -0.1700
Data Index: 118732 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9632. Min Act: -0.1700
Data Index: 3202519 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9632. Min Act: -0.1700
Data Index: 1394015 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9320. Min Act: -0.1700
Data Index: 2704498 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9320. Min Act: -0.1700
Data Index: 1943905 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9320. Min Act: -0.1700
Data Index: 7982304 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9007. Min Act: -0.1700
Data Index: 5024525 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9007. Min Act: -0.1700
Data Index: 3791788 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9007. Min Act: -0.1700
Data Index: 7097844 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.9007. Min Act: -0.1700
Data Index: 2726167 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 7766875 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 8524793 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 4137903 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 4524475 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 4052620 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 4064772 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8695. Min Act: -0.1700
Data Index: 2236101 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8382. Min Act: -0.1700
Data Index: 4797780 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3070. Min Range: -7.3070
Max Act: 6.8382. Min Act: -0.1700
Data Index: 4840872 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19