Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2119 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.3300. Min Act: -0.1700
Data Index: 7031937 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.2362. Min Act: -0.1700
Data Index: 3877771 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.2675. Min Act: -0.1700
Data Index: 7720647 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.2050. Min Act: -0.1700
Data Index: 8230513 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.1737. Min Act: -0.1700
Data Index: 8534499 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.1425. Min Act: -0.1700
Data Index: 5728107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.1425. Min Act: -0.1700
Data Index: 2174015 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.1112. Min Act: -0.1700
Data Index: 6271275 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0799. Min Act: -0.1700
Data Index: 1820593 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0799. Min Act: -0.1700
Data Index: 5857118 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0487. Min Act: -0.1700
Data Index: 237255 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0487. Min Act: -0.1700
Data Index: 7396542 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0487. Min Act: -0.1700
Data Index: 6629213 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0487. Min Act: -0.1700
Data Index: 2029099 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0487. Min Act: -0.1700
Data Index: 5320601 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0174. Min Act: -0.1700
Data Index: 8384742 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3300. Min Range: -4.3300
Max Act: 4.0487. Min Act: -0.1700
Data Index: 1667845 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3300. Min Range: -4.3300
Max Act: 3.9862. Min Act: -0.1700
Data Index: 1345056 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3300. Min Range: -4.3300
Max Act: 3.9862. Min Act: -0.1700
Data Index: 7757680 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3300. Min Range: -4.3300
Max Act: 3.9862. Min Act: -0.1700
Data Index: 3898682 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19