Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.2119. Min Act: -0.1700
Data Index: 3318995 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.1807. Min Act: -0.1700
Data Index: 5632956 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.0557. Min Act: -0.1700
Data Index: 4126135 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2119. Min Range: -7.2119
Max Act: 7.0557. Min Act: -0.1700
Data Index: 7794738 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.9619. Min Act: -0.1700
Data Index: 2618929 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.9619. Min Act: -0.1700
Data Index: 7220129 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8682. Min Act: -0.1700
Data Index: 2960019 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.8057. Min Act: -0.1700
Data Index: 5048546 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 2296992 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 1495546 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 1976124 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 5925677 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7744. Min Act: -0.1700
Data Index: 1355615 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7432. Min Act: -0.1700
Data Index: 7008206 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7432. Min Act: -0.1700
Data Index: 3888368 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.7119. Min Act: -0.1700
Data Index: 2476912 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.6807. Min Act: -0.1700
Data Index: 5868982 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.6807. Min Act: -0.1700
Data Index: 1381464 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.5869. Min Act: -0.1700
Data Index: 6970466 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2119. Min Range: -7.2119
Max Act: 6.6182. Min Act: -0.1700
Data Index: 6976568 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19