Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.6444. Min Act: -0.1700
Data Index: 311636 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.6131. Min Act: -0.1700
Data Index: 2678926 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.6131. Min Act: -0.1700
Data Index: 7029526 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 570488 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.5819. Min Act: -0.1700
Data Index: 8289966 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.5506. Min Act: -0.1700
Data Index: 8565103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.5506. Min Act: -0.1700
Data Index: 3107664 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.5194. Min Act: -0.1700
Data Index: 570487 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.5194. Min Act: -0.1700
Data Index: 5569538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4881. Min Act: -0.1700
Data Index: 570489 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 5055922 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 4929125 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 8218961 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 2019197 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 2004727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 1141150 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 7263057 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 343026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 1151269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6444. Min Range: -5.6444
Max Act: 5.4569. Min Act: -0.1700
Data Index: 148719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19