Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4840 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.5888. Min Act: -0.1700
Data Index: 3459548 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.5263. Min Act: -0.1700
Data Index: 5855399 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.4951. Min Act: -0.1700
Data Index: 1666741 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.4326. Min Act: -0.1700
Data Index: 3494066 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.4326. Min Act: -0.1700
Data Index: 5465624 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.4013. Min Act: -0.1700
Data Index: 2132846 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.4013. Min Act: -0.1700
Data Index: 4739229 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 2147926 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3700. Min Act: -0.1700
Data Index: 133998 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3700. Min Act: -0.1700
Data Index: 2191208 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 6043111 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 7954483 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 4815018 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 451240 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3700. Min Act: -0.1700
Data Index: 4810212 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 252061 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3388. Min Act: -0.1700
Data Index: 8498952 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.2763. Min Act: -0.1700
Data Index: 3435375 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3075. Min Act: -0.1700
Data Index: 784666 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5888. Min Range: -4.5888
Max Act: 4.3075. Min Act: -0.1700
Data Index: 5003494 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19