Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 318 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0154. Min Range: -8.0154
Max Act: 8.0154. Min Act: -0.1700
Data Index: 2746067 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.9216. Min Act: -0.1700
Data Index: 2294271 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.9216. Min Act: -0.1700
Data Index: 3182026 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.8904. Min Act: -0.1700
Data Index: 225362 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.7341. Min Act: -0.1700
Data Index: 7588933 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.7029. Min Act: -0.1700
Data Index: 771078 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.7029. Min Act: -0.1700
Data Index: 352525 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.6716. Min Act: -0.1700
Data Index: 7198241 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.7029. Min Act: -0.1700
Data Index: 4899681 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.6091. Min Act: -0.1700
Data Index: 1263216 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.6716. Min Act: -0.1700
Data Index: 1829088 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.5466. Min Act: -0.1700
Data Index: 1894029 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.5466. Min Act: -0.1700
Data Index: 1114509 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.5779. Min Act: -0.1700
Data Index: 2919869 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.5466. Min Act: -0.1700
Data Index: 1928529 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.5154. Min Act: -0.1700
Data Index: 838870 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.4841. Min Act: -0.1700
Data Index: 1787432 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.4216. Min Act: -0.1700
Data Index: 2184965 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.4216. Min Act: -0.1700
Data Index: 488778 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0154. Min Range: -8.0154
Max Act: 7.3904. Min Act: -0.1700
Data Index: 3289563 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19