Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.4951. Min Act: -0.1700
Data Index: 36057 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.8389. Min Act: -0.1700
Data Index: 3766533 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.6514. Min Act: -0.1700
Data Index: 1402786 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.6201. Min Act: -0.1700
Data Index: 5403508 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.5264. Min Act: -0.1700
Data Index: 4732943 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.5264. Min Act: -0.1700
Data Index: 8194702 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.4951. Min Act: -0.1700
Data Index: 6114545 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.4639. Min Act: -0.1700
Data Index: 105090 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.4014. Min Act: -0.1700
Data Index: 5167397 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.4014. Min Act: -0.1700
Data Index: 4986941 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.4326. Min Act: -0.1700
Data Index: 4799425 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.3389. Min Act: -0.1700
Data Index: 4732939 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.3389. Min Act: -0.1700
Data Index: 167705 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1478585 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.3076. Min Act: -0.1700
Data Index: 1984394 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.3076. Min Act: -0.1700
Data Index: 4732941 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.3076. Min Act: -0.1700
Data Index: 8300890 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.2764. Min Act: -0.1700
Data Index: 4652458 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.2764. Min Act: -0.1700
Data Index: 1506654 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.2139. Min Act: -0.1700
Data Index: 7578055 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19