Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.9919. Min Act: -0.1700
Data Index: 7153712 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.8669. Min Act: -0.1700
Data Index: 4445427 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.8044. Min Act: -0.1700
Data Index: 4520512 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.8044. Min Act: -0.1700
Data Index: 106676 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.8044. Min Act: -0.1700
Data Index: 1426445 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7731. Min Act: -0.1700
Data Index: 888500 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7731. Min Act: -0.1700
Data Index: 6180139 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7731. Min Act: -0.1700
Data Index: 2871968 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7731. Min Act: -0.1700
Data Index: 2409740 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7419. Min Act: -0.1700
Data Index: 7024840 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7419. Min Act: -0.1700
Data Index: 5643432 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.7106. Min Act: -0.1700
Data Index: 7958568 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6481. Min Act: -0.1700
Data Index: 611208 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6794. Min Act: -0.1700
Data Index: 4823546 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6794. Min Act: -0.1700
Data Index: 3695429 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6794. Min Act: -0.1700
Data Index: 4463792 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6481. Min Act: -0.1700
Data Index: 2747678 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6481. Min Act: -0.1700
Data Index: 6782982 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6169. Min Act: -0.1700
Data Index: 227260 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9919. Min Range: -5.9919
Max Act: 5.6169. Min Act: -0.1700
Data Index: 8325671 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19