Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5441 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.6956. Min Act: -0.1700
Data Index: 785577 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.6331. Min Act: -0.1700
Data Index: 5189638 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.5394. Min Act: -0.1700
Data Index: 2742598 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.4769. Min Act: -0.1700
Data Index: 4306224 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.4769. Min Act: -0.1700
Data Index: 8232288 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.4456. Min Act: -0.1700
Data Index: 6492397 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.4144. Min Act: -0.1700
Data Index: 8342239 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.4144. Min Act: -0.1700
Data Index: 7082800 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3519. Min Act: -0.1700
Data Index: 3676794 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3831. Min Act: -0.1700
Data Index: 8202499 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3519. Min Act: -0.1700
Data Index: 5189639 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3206. Min Act: -0.1700
Data Index: 1957397 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3206. Min Act: -0.1700
Data Index: 4915719 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3206. Min Act: -0.1700
Data Index: 1827253 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3206. Min Act: -0.1700
Data Index: 5189640 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.3206. Min Act: -0.1700
Data Index: 344240 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.2894. Min Act: -0.1700
Data Index: 2554185 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.2894. Min Act: -0.1700
Data Index: 8693161 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.2894. Min Act: -0.1700
Data Index: 8063527 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6956. Min Range: -7.6956
Max Act: 7.2269. Min Act: -0.1700
Data Index: 1519885 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19