Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2253 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.3161. Min Act: -0.1700
Data Index: 8670211 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1911. Min Act: -0.1700
Data Index: 689964 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1598. Min Act: -0.1700
Data Index: 3618864 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1286. Min Act: -0.1700
Data Index: 4401898 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1911. Min Act: -0.1700
Data Index: 6864032 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1286. Min Act: -0.1700
Data Index: 6027181 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1286. Min Act: -0.1700
Data Index: 2135223 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.0036. Min Act: -0.1700
Data Index: 3051648 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.0348. Min Act: -0.1700
Data Index: 1752966 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9098. Min Act: -0.1700
Data Index: 7633863 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9098. Min Act: -0.1700
Data Index: 2612568 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8786. Min Act: -0.1700
Data Index: 1556109 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8786. Min Act: -0.1700
Data Index: 7366763 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8473. Min Act: -0.1700
Data Index: 4029653 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9098. Min Act: -0.1700
Data Index: 8739164 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8473. Min Act: -0.1700
Data Index: 6912821 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8161. Min Act: -0.1700
Data Index: 4028726 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8161. Min Act: -0.1700
Data Index: 7806800 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7848. Min Act: -0.1700
Data Index: 5883292 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7536. Min Act: -0.1700
Data Index: 965426 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19