Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.7461. Min Act: -0.1700
Data Index: 6320078 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.7148. Min Act: -0.1700
Data Index: 3680901 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6835. Min Act: -0.1700
Data Index: 2759061 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6835. Min Act: -0.1700
Data Index: 2797016 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6835. Min Act: -0.1700
Data Index: 6651635 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6835. Min Act: -0.1700
Data Index: 1343395 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6522. Min Act: -0.1700
Data Index: 6146259 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6835. Min Act: -0.1700
Data Index: 54529 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6522. Min Act: -0.1700
Data Index: 4722450 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6522. Min Act: -0.1700
Data Index: 3690201 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6522. Min Act: -0.1700
Data Index: 1366069 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6522. Min Act: -0.1700
Data Index: 8189463 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6522. Min Act: -0.1700
Data Index: 6342786 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 248110 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 4119822 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 4200164 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 3612914 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 4888819 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 5039675 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.6209. Min Act: -0.1700
Data Index: 5606843 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19