Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1779 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0446. Min Range: -5.0446
Max Act: 5.0446. Min Act: -0.1700
Data Index: 841591 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.7008. Min Act: -0.1697
Data Index: 2795826 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.6383. Min Act: -0.1700
Data Index: 4221607 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.6383. Min Act: -0.1699
Data Index: 5435794 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.6071. Min Act: -0.1700
Data Index: 8595727 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.6071. Min Act: -0.1700
Data Index: 8528470 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.6071. Min Act: -0.1700
Data Index: 6274288 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5758. Min Act: -0.1700
Data Index: 2159370 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5758. Min Act: -0.1700
Data Index: 4813619 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5446. Min Act: -0.1700
Data Index: 8008426 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5133. Min Act: -0.1700
Data Index: 4571662 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5133. Min Act: -0.1699
Data Index: 667399 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5133. Min Act: -0.1700
Data Index: 88165 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5133. Min Act: -0.1700
Data Index: 4089213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.5133. Min Act: -0.1700
Data Index: 7880131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.4821. Min Act: -0.1700
Data Index: 6876419 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.4821. Min Act: -0.1700
Data Index: 5223200 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.4508. Min Act: -0.1700
Data Index: 3583730 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.4508. Min Act: -0.1699
Data Index: 7010095 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0446. Min Range: -5.0446
Max Act: 4.4821. Min Act: -0.1698
Data Index: 8589551 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19