Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.2886. Min Act: -0.1700
Data Index: 7641270 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.2886. Min Act: -0.1700
Data Index: 8752460 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.2261. Min Act: -0.1700
Data Index: 1772847 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.2886. Min Act: -0.1700
Data Index: 2554721 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.2261. Min Act: -0.1700
Data Index: 3457878 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.1324. Min Act: -0.1700
Data Index: 6208029 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.1324. Min Act: -0.1700
Data Index: 90968 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.0699. Min Act: -0.1700
Data Index: 2554722 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.0386. Min Act: -0.1700
Data Index: 1726210 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.0386. Min Act: -0.1700
Data Index: 7641264 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.0074. Min Act: -0.1700
Data Index: 8813292 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2886. Min Range: -8.2886
Max Act: 8.0074. Min Act: -0.1700
Data Index: 90971 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9761. Min Act: -0.1700
Data Index: 90966 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9449. Min Act: -0.1700
Data Index: 6554681 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9761. Min Act: -0.1700
Data Index: 6815984 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9449. Min Act: -0.1700
Data Index: 7954142 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9449. Min Act: -0.1700
Data Index: 1772844 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.8824. Min Act: -0.1700
Data Index: 4889097 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9136. Min Act: -0.1700
Data Index: 90964 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2886. Min Range: -8.2886
Max Act: 7.9136. Min Act: -0.1700
Data Index: 7641275 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19