Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.4211. Min Act: -0.1700
Data Index: 1096613 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.2649. Min Act: -0.1700
Data Index: 2706151 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.2649. Min Act: -0.1700
Data Index: 1388929 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.2649. Min Act: -0.1700
Data Index: 4371129 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.1711. Min Act: -0.1700
Data Index: 6420732 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.1086. Min Act: -0.1700
Data Index: 6479736 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.0774. Min Act: -0.1700
Data Index: 8062083 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.0774. Min Act: -0.1700
Data Index: 8347677 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4211. Min Range: -5.4211
Max Act: 5.0461. Min Act: -0.1700
Data Index: 644426 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.9836. Min Act: -0.1700
Data Index: 6174341 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.9524. Min Act: -0.1700
Data Index: 6966219 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.9836. Min Act: -0.1700
Data Index: 2584719 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.9524. Min Act: -0.1700
Data Index: 8347685 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.9524. Min Act: -0.1700
Data Index: 7582631 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.8586. Min Act: -0.1700
Data Index: 6850297 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.8586. Min Act: -0.1700
Data Index: 4903157 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.8586. Min Act: -0.1700
Data Index: 2886435 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.8586. Min Act: -0.1700
Data Index: 8098950 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.8274. Min Act: -0.1700
Data Index: 6966878 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4211. Min Range: -5.4211
Max Act: 4.8274. Min Act: -0.1700
Data Index: 7698089 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19