Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1518. Min Range: -7.1518
Max Act: 7.1518. Min Act: -0.1700
Data Index: 7545057 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1518. Min Range: -7.1518
Max Act: 7.0581. Min Act: -0.1700
Data Index: 2685765 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.9956. Min Act: -0.1700
Data Index: 8180929 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.9643. Min Act: -0.1700
Data Index: 610949 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.9643. Min Act: -0.1700
Data Index: 2153038 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.9331. Min Act: -0.1700
Data Index: 7061139 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.9331. Min Act: -0.1700
Data Index: 1075288 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8706. Min Act: -0.1700
Data Index: 6934009 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8706. Min Act: -0.1700
Data Index: 6603836 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8393. Min Act: -0.1700
Data Index: 6722023 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8706. Min Act: -0.1700
Data Index: 7783502 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.7768. Min Act: -0.1700
Data Index: 7136398 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8081. Min Act: -0.1700
Data Index: 8556488 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8081. Min Act: -0.1700
Data Index: 3040209 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8393. Min Act: -0.1700
Data Index: 8398507 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.7768. Min Act: -0.1700
Data Index: 2038739 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8081. Min Act: -0.1700
Data Index: 3319995 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8393. Min Act: -0.1700
Data Index: 7150601 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.8081. Min Act: -0.1700
Data Index: 3226577 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.7768. Min Act: -0.1700
Data Index: 5267538 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19