Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1724. Min Range: -7.1724
Max Act: 7.1724. Min Act: -0.1700
Data Index: 6947236 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1724. Min Range: -7.1724
Max Act: 7.0161. Min Act: -0.1700
Data Index: 4021935 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.9536. Min Act: -0.1700
Data Index: 5802762 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.8911. Min Act: -0.1700
Data Index: 4057928 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.8911. Min Act: -0.1700
Data Index: 2880166 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.8286. Min Act: -0.1700
Data Index: 4021925 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.8286. Min Act: -0.1700
Data Index: 7514778 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.6724. Min Act: -0.1700
Data Index: 5844602 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.6099. Min Act: -0.1700
Data Index: 1336172 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.6099. Min Act: -0.1700
Data Index: 5525348 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.6099. Min Act: -0.1700
Data Index: 6905656 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.5786. Min Act: -0.1700
Data Index: 131554 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.5474. Min Act: -0.1700
Data Index: 5018074 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.5786. Min Act: -0.1700
Data Index: 309914 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.5161. Min Act: -0.1700
Data Index: 6082490 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.5161. Min Act: -0.1700
Data Index: 6911614 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.5161. Min Act: -0.1700
Data Index: 2264058 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.4224. Min Act: -0.1700
Data Index: 3913670 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.4224. Min Act: -0.1700
Data Index: 6004916 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1724. Min Range: -7.1724
Max Act: 6.4224. Min Act: -0.1700
Data Index: 717533 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19