Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.7081. Min Act: -0.1700
Data Index: 263309 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.5206. Min Act: -0.1700
Data Index: 3034610 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.5206. Min Act: -0.1700
Data Index: 6505649 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.3956. Min Act: -0.1700
Data Index: 566384 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.3956. Min Act: -0.1700
Data Index: 442602 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.3644. Min Act: -0.1700
Data Index: 2537452 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.3331. Min Act: -0.1700
Data Index: 5482379 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.3019. Min Act: -0.1700
Data Index: 1865691 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.2081. Min Act: -0.1700
Data Index: 2275118 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.2081. Min Act: -0.1700
Data Index: 8607152 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.2394. Min Act: -0.1700
Data Index: 4090812 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.1144. Min Act: -0.1700
Data Index: 4977820 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.1144. Min Act: -0.1700
Data Index: 20391 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.1144. Min Act: -0.1700
Data Index: 467235 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.0831. Min Act: -0.1700
Data Index: 2888974 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.0831. Min Act: -0.1700
Data Index: 701666 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.0831. Min Act: -0.1700
Data Index: 1521649 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.0206. Min Act: -0.1700
Data Index: 2436767 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.0206. Min Act: -0.1700
Data Index: 1947268 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7081. Min Range: -5.7081
Max Act: 5.0206. Min Act: -0.1700
Data Index: 1517849 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19