Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2497 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.8781. Min Act: -0.1700
Data Index: 6374057 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.8156. Min Act: -0.1700
Data Index: 7207669 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.7843. Min Act: -0.1700
Data Index: 6971833 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.8156. Min Act: -0.1700
Data Index: 1536176 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.7531. Min Act: -0.1700
Data Index: 6177754 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.7531. Min Act: -0.1700
Data Index: 6528072 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.7218. Min Act: -0.1700
Data Index: 1937999 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.7218. Min Act: -0.1700
Data Index: 5587654 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6906. Min Act: -0.1700
Data Index: 5516783 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6593. Min Act: -0.1700
Data Index: 2615419 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6593. Min Act: -0.1700
Data Index: 5806166 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6906. Min Act: -0.1700
Data Index: 2646706 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6593. Min Act: -0.1700
Data Index: 1587966 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6906. Min Act: -0.1700
Data Index: 7968685 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6593. Min Act: -0.1700
Data Index: 4803617 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6281. Min Act: -0.1700
Data Index: 121732 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6281. Min Act: -0.1700
Data Index: 345760 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6281. Min Act: -0.1700
Data Index: 7245497 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6281. Min Act: -0.1700
Data Index: 2405882 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8781. Min Range: -4.8781
Max Act: 4.6281. Min Act: -0.1700
Data Index: 7413124 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19