Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 482 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3864. Min Range: -7.3864
Max Act: 7.3864. Min Act: -0.1700
Data Index: 3820133 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3864. Min Range: -7.3864
Max Act: 7.2927. Min Act: -0.1700
Data Index: 1641960 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3864. Min Range: -7.3864
Max Act: 7.1677. Min Act: -0.1700
Data Index: 6930294 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3864. Min Range: -7.3864
Max Act: 7.0427. Min Act: -0.1700
Data Index: 671004 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3864. Min Range: -7.3864
Max Act: 7.0114. Min Act: -0.1700
Data Index: 3238618 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3864. Min Range: -7.3864
Max Act: 7.0114. Min Act: -0.1700
Data Index: 2961639 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.9489. Min Act: -0.1700
Data Index: 3517465 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.9177. Min Act: -0.1700
Data Index: 116858 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.8864. Min Act: -0.1700
Data Index: 4660544 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.8552. Min Act: -0.1700
Data Index: 2487738 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.8552. Min Act: -0.1700
Data Index: 7004213 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.8239. Min Act: -0.1700
Data Index: 1645810 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7927. Min Act: -0.1700
Data Index: 1211306 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7927. Min Act: -0.1700
Data Index: 1159607 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7927. Min Act: -0.1700
Data Index: 3312003 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.8239. Min Act: -0.1700
Data Index: 8582624 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7302. Min Act: -0.1700
Data Index: 7963189 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7302. Min Act: -0.1700
Data Index: 4915845 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7302. Min Act: -0.1700
Data Index: 5571122 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3864. Min Range: -7.3864
Max Act: 6.7302. Min Act: -0.1700
Data Index: 4604711 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19