Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5328 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.8768. Min Act: -0.1700
Data Index: 7340169 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.8143. Min Act: -0.1700
Data Index: 817448 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.7831. Min Act: -0.1700
Data Index: 1431542 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.7518. Min Act: -0.1700
Data Index: 6785195 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.7206. Min Act: -0.1700
Data Index: 1255585 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.6268. Min Act: -0.1700
Data Index: 6867346 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.6268. Min Act: -0.1700
Data Index: 1220274 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.6268. Min Act: -0.1700
Data Index: 4069902 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.6268. Min Act: -0.1700
Data Index: 4630503 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.5331. Min Act: -0.1700
Data Index: 5938427 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.5643. Min Act: -0.1700
Data Index: 4966358 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.5331. Min Act: -0.1700
Data Index: 3147682 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.5331. Min Act: -0.1700
Data Index: 893688 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.4393. Min Act: -0.1700
Data Index: 8270104 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.4706. Min Act: -0.1700
Data Index: 5147354 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.4393. Min Act: -0.1700
Data Index: 3901694 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.4393. Min Act: -0.1700
Data Index: 8293319 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.4081. Min Act: -0.1700
Data Index: 7807335 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.3456. Min Act: -0.1700
Data Index: 5946683 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8768. Min Range: -6.8768
Max Act: 6.3768. Min Act: -0.1700
Data Index: 550838 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19