Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 102 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0157. Min Range: -4.0157
Max Act: 4.0157. Min Act: -0.1700
Data Index: 7856322 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0157. Min Range: -4.0157
Max Act: 4.0157. Min Act: -0.1700
Data Index: 4577706 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.9532. Min Act: -0.1700
Data Index: 7499429 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.8907. Min Act: -0.1700
Data Index: 7638480 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.8281. Min Act: -0.1700
Data Index: 8355521 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.8125. Min Act: -0.1700
Data Index: 1440634 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.7969. Min Act: -0.1700
Data Index: 5455910 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.7187. Min Act: -0.1700
Data Index: 4507361 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6874. Min Act: -0.1700
Data Index: 3000059 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6717. Min Act: -0.1700
Data Index: 1680199 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6874. Min Act: -0.1700
Data Index: 7063339 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6874. Min Act: -0.1700
Data Index: 346500 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6717. Min Act: -0.1700
Data Index: 4028005 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6717. Min Act: -0.1700
Data Index: 1345803 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6404. Min Act: -0.1700
Data Index: 6276007 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6404. Min Act: -0.1700
Data Index: 6051404 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6091. Min Act: -0.1700
Data Index: 675102 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6248. Min Act: -0.1700
Data Index: 6729408 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6091. Min Act: -0.1700
Data Index: 4641996 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0157. Min Range: -4.0157
Max Act: 3.6091. Min Act: -0.1700
Data Index: 433750 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19