Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4669 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.8122. Min Act: -0.1700
Data Index: 8038169 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6352019 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.6872. Min Act: -0.1700
Data Index: 6380189 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.6559. Min Act: -0.1700
Data Index: 397434 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.6559. Min Act: -0.1700
Data Index: 5568539 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5934. Min Act: -0.1700
Data Index: 6068731 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.6247. Min Act: -0.1700
Data Index: 3611337 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5934. Min Act: -0.1700
Data Index: 7412391 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5934. Min Act: -0.1700
Data Index: 8792972 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5934. Min Act: -0.1700
Data Index: 960040 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 7426658 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5934. Min Act: -0.1700
Data Index: 2868976 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 5266412 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 5705046 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 1132806 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5309. Min Act: -0.1700
Data Index: 4119814 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 3959021 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5309. Min Act: -0.1700
Data Index: 2779306 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 7305387 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8122. Min Range: -4.8122
Max Act: 4.5622. Min Act: -0.1700
Data Index: 3179885 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19