Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.9295. Min Act: -0.1700
Data Index: 6316289 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.8357. Min Act: -0.1700
Data Index: 5510448 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.8045. Min Act: -0.1700
Data Index: 351032 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.7732. Min Act: -0.1700
Data Index: 4351177 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.7419. Min Act: -0.1700
Data Index: 1322334 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.7106. Min Act: -0.1700
Data Index: 3360045 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.7106. Min Act: -0.1700
Data Index: 5682494 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6168. Min Act: -0.1700
Data Index: 1017048 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6168. Min Act: -0.1700
Data Index: 700143 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6480. Min Act: -0.1700
Data Index: 2227385 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6480. Min Act: -0.1700
Data Index: 3338344 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6480. Min Act: -0.1700
Data Index: 1017050 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6168. Min Act: -0.1700
Data Index: 426126 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6168. Min Act: -0.1700
Data Index: 1467703 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6168. Min Act: -0.1700
Data Index: 1578565 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.5854. Min Act: -0.1700
Data Index: 5587807 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.6168. Min Act: -0.1700
Data Index: 2576349 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.5854. Min Act: -0.1700
Data Index: 2469632 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.5541. Min Act: -0.1700
Data Index: 732230 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9295. Min Range: -3.9295
Max Act: 3.5854. Min Act: -0.1700
Data Index: 1017047 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19