Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2231 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 4615644 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.6371. Min Act: -0.1700
Data Index: 7525245 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.6684. Min Act: -0.1700
Data Index: 1135266 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.6371. Min Act: -0.1700
Data Index: 3643656 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.5746. Min Act: -0.1700
Data Index: 1173819 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.5746. Min Act: -0.1700
Data Index: 5616521 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.5746. Min Act: -0.1700
Data Index: 7634533 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 6219634 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 5289453 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 2579986 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 6682319 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 4783689 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4184. Min Act: -0.1700
Data Index: 3969997 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4184. Min Act: -0.1700
Data Index: 5309568 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 3230986 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 520881 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 3438960 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 4427762 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 6480188 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.2934. Min Act: -0.1700
Data Index: 1961593 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19