Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3040. Min Range: -6.3040
Max Act: 6.3040. Min Act: -0.1700
Data Index: 8325247 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3040. Min Range: -6.3040
Max Act: 6.0540. Min Act: -0.1700
Data Index: 6366223 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.9602. Min Act: -0.1700
Data Index: 3400018 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.9290. Min Act: -0.1700
Data Index: 5078508 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.9290. Min Act: -0.1700
Data Index: 3918660 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8977. Min Act: -0.1700
Data Index: 2543298 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8665. Min Act: -0.1700
Data Index: 5403376 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8665. Min Act: -0.1700
Data Index: 673510 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8352. Min Act: -0.1700
Data Index: 1475961 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8352. Min Act: -0.1700
Data Index: 3656028 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8040. Min Act: -0.1700
Data Index: 2016551 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8040. Min Act: -0.1700
Data Index: 392010 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.8040. Min Act: -0.1700
Data Index: 8177962 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.7727. Min Act: -0.1700
Data Index: 8058799 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.7727. Min Act: -0.1700
Data Index: 3275279 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.7102. Min Act: -0.1700
Data Index: 4665547 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.7102. Min Act: -0.1700
Data Index: 3414622 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.7102. Min Act: -0.1700
Data Index: 4851799 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.7102. Min Act: -0.1700
Data Index: 8063542 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3040. Min Range: -6.3040
Max Act: 5.6790. Min Act: -0.1700
Data Index: 1427542 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19