Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0213. Min Range: -4.0213
Max Act: 4.0213. Min Act: -0.1700
Data Index: 6476098 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0213. Min Range: -4.0213
Max Act: 4.0213. Min Act: -0.1700
Data Index: 7553996 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0213. Min Range: -4.0213
Max Act: 4.0213. Min Act: -0.1700
Data Index: 7735031 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9900. Min Act: -0.1700
Data Index: 8390157 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9900. Min Act: -0.1700
Data Index: 87789 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9900. Min Act: -0.1700
Data Index: 5692542 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9900. Min Act: -0.1700
Data Index: 2324716 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9588. Min Act: -0.1700
Data Index: 1474140 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9588. Min Act: -0.1700
Data Index: 815004 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9588. Min Act: -0.1700
Data Index: 3440596 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9588. Min Act: -0.1700
Data Index: 8582648 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 2283762 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 4236395 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 4712122 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 5084175 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 5248653 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 1232749 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9588. Min Act: -0.1700
Data Index: 2199053 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 2491635 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0213. Min Range: -4.0213
Max Act: 3.9275. Min Act: -0.1700
Data Index: 5743871 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19