Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2141573 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.4707. Min Act: -0.1700
Data Index: 4896943 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.4395. Min Act: -0.1700
Data Index: 6911767 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.3770. Min Act: -0.1700
Data Index: 8275289 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.3770. Min Act: -0.1700
Data Index: 2437189 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.3770. Min Act: -0.1700
Data Index: 3862749 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 5197482 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 4151245 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.3145. Min Act: -0.1700
Data Index: 2703444 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.3145. Min Act: -0.1700
Data Index: 3030808 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 3896869 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 3884298 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.3145. Min Act: -0.1700
Data Index: 582 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 1255347 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 8410171 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2832. Min Act: -0.1700
Data Index: 1980480 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2520. Min Act: -0.1700
Data Index: 8615307 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2520. Min Act: -0.1700
Data Index: 8722021 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2520. Min Act: -0.1700
Data Index: 8444933 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4707. Min Range: -4.4707
Max Act: 4.2207. Min Act: -0.1700
Data Index: 3892219 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19