Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.7740. Min Act: -0.1700
Data Index: 5933588 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.7427. Min Act: -0.1700
Data Index: 6447038 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.7115. Min Act: -0.1700
Data Index: 1288106 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.7115. Min Act: -0.1700
Data Index: 7401514 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6802. Min Act: -0.1700
Data Index: 5866443 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6490. Min Act: -0.1700
Data Index: 6563760 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6490. Min Act: -0.1700
Data Index: 908264 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6490. Min Act: -0.1700
Data Index: 224634 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6177. Min Act: -0.1700
Data Index: 1288105 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6490. Min Act: -0.1700
Data Index: 1637733 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6177. Min Act: -0.1700
Data Index: 616028 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6177. Min Act: -0.1700
Data Index: 8532827 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6177. Min Act: -0.1700
Data Index: 2649026 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6177. Min Act: -0.1700
Data Index: 2094210 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.6177. Min Act: -0.1700
Data Index: 7328953 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.5865. Min Act: -0.1700
Data Index: 4797592 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.5552. Min Act: -0.1700
Data Index: 1182206 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.5865. Min Act: -0.1700
Data Index: 4797590 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2405870 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7740. Min Range: -5.7740
Max Act: 5.5552. Min Act: -0.1700
Data Index: 1288100 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19