Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.4116. Min Act: -0.1700
Data Index: 2408779 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.3179. Min Act: -0.1700
Data Index: 3556109 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.2554. Min Act: -0.1487
Data Index: 2684979 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.2554. Min Act: -0.1692
Data Index: 6368524 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.2554. Min Act: -0.1700
Data Index: 1458354 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1929. Min Act: -0.1700
Data Index: 4112738 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1700
Data Index: 3346571 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1700
Data Index: 1190143 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1700
Data Index: 8211791 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1700
Data Index: 3901996 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1700
Data Index: 237703 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1697
Data Index: 7082354 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1616. Min Act: -0.1700
Data Index: 7092783 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0991. Min Act: -0.1700
Data Index: 2684982 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0991. Min Act: -0.1700
Data Index: 3568118 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0991. Min Act: -0.1700
Data Index: 3546560 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0679. Min Act: -0.1699
Data Index: 7092782 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 456039 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 4835451 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 5943474 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19