Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6363 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.1489. Min Act: -0.1700
Data Index: 2734027 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.0239. Min Act: -0.1700
Data Index: 6397093 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.0552. Min Act: -0.1700
Data Index: 1028126 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.0552. Min Act: -0.1700
Data Index: 3974617 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 8771784 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 7017136 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 3621068 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 8603407 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 7250155 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8677. Min Act: -0.1700
Data Index: 2610110 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8677. Min Act: -0.1700
Data Index: 8466252 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 7240007 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3386912 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 7205631 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 2708062 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8052. Min Act: -0.1700
Data Index: 7250154 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 441066 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8052. Min Act: -0.1700
Data Index: 8662125 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8052. Min Act: -0.1700
Data Index: 6216912 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8052. Min Act: -0.1700
Data Index: 2069674 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19