Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.1356. Min Act: -0.1700
Data Index: 4127770 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.1198. Min Act: -0.1700
Data Index: 7312259 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.1040. Min Act: -0.1700
Data Index: 1218650 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0883. Min Act: -0.1700
Data Index: 6934510 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0883. Min Act: -0.1700
Data Index: 2070843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0725. Min Act: -0.1700
Data Index: 8707740 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0725. Min Act: -0.1700
Data Index: 1431629 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0725. Min Act: -0.1700
Data Index: 7635015 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0725. Min Act: -0.1700
Data Index: 7118871 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0567. Min Act: -0.1700
Data Index: 4516899 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0410. Min Act: -0.1700
Data Index: 854488 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0410. Min Act: -0.1700
Data Index: 8131302 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0410. Min Act: -0.1700
Data Index: 1713779 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 8632896 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 6587976 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 8255276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 1839397 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 4463171 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 3780628 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1356. Min Range: -3.1356
Max Act: 3.0252. Min Act: -0.1700
Data Index: 8450594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19