Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4447 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.5640. Min Act: -0.1700
Data Index: 6167539 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.4390. Min Act: -0.1700
Data Index: 4591490 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3765. Min Act: -0.1700
Data Index: 902352 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.4077. Min Act: -0.1700
Data Index: 2279798 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3765. Min Act: -0.1700
Data Index: 4656614 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3765. Min Act: -0.1700
Data Index: 5477420 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3452. Min Act: -0.1700
Data Index: 7274530 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3140. Min Act: -0.1700
Data Index: 7898692 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3140. Min Act: -0.1700
Data Index: 7846591 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3140. Min Act: -0.1700
Data Index: 31842 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.3140. Min Act: -0.1700
Data Index: 1285518 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2827. Min Act: -0.1700
Data Index: 684221 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2827. Min Act: -0.1700
Data Index: 30904 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 5021599 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 888506 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 1164687 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 4022816 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 1742954 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 273372 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5640. Min Range: -6.5640
Max Act: 6.2515. Min Act: -0.1700
Data Index: 4656626 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19