Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3313 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9706. Min Range: -10.9706
Max Act: 10.9706. Min Act: -0.1700
Data Index: 8436085 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9706. Min Range: -10.9706
Max Act: 10.4081. Min Act: -0.1700
Data Index: 8742030 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9706. Min Range: -10.9706
Max Act: 10.4081. Min Act: -0.1700
Data Index: 2519803 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9706. Min Range: -10.9706
Max Act: 10.3456. Min Act: -0.1700
Data Index: 4851378 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9706. Min Range: -10.9706
Max Act: 10.2831. Min Act: -0.1700
Data Index: 6218828 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9706. Min Range: -10.9706
Max Act: 10.2206. Min Act: -0.1700
Data Index: 4014262 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.8456. Min Act: -0.1700
Data Index: 7339654 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.8456. Min Act: -0.1700
Data Index: 3918890 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.8456. Min Act: -0.1700
Data Index: 3913572 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.6581. Min Act: -0.1700
Data Index: 6524689 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.7206. Min Act: -0.1700
Data Index: 1278300 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.6581. Min Act: -0.1700
Data Index: 5234362 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.5956. Min Act: -0.1700
Data Index: 7818664 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.5331. Min Act: -0.1700
Data Index: 313118 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.5331. Min Act: -0.1700
Data Index: 2559435 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.5331. Min Act: -0.1700
Data Index: 6868784 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.4706. Min Act: -0.1700
Data Index: 615080 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.4706. Min Act: -0.1700
Data Index: 6624500 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.4081. Min Act: -0.1700
Data Index: 868413 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9706. Min Range: -10.9706
Max Act: 9.3456. Min Act: -0.1700
Data Index: 6380 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19