Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1022. Min Range: -6.1022
Max Act: 6.1022. Min Act: -0.1700
Data Index: 5937469 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7897. Min Act: -0.1700
Data Index: 3111531 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.8209. Min Act: -0.1700
Data Index: 8615389 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.8209. Min Act: -0.1700
Data Index: 1212965 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7897. Min Act: -0.1700
Data Index: 8660222 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7897. Min Act: -0.1700
Data Index: 314629 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7584. Min Act: -0.1700
Data Index: 4239914 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7272. Min Act: -0.1700
Data Index: 2777469 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7584. Min Act: -0.1700
Data Index: 1804442 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7272. Min Act: -0.1700
Data Index: 709432 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.7272. Min Act: -0.1700
Data Index: 1516500 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 1193406 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 5314696 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 3050860 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6334. Min Act: -0.1700
Data Index: 2460958 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4088746 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 2500861 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 6865132 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.5709. Min Act: -0.1700
Data Index: 7304555 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1022. Min Range: -6.1022
Max Act: 5.5709. Min Act: -0.1700
Data Index: 6508001 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19