Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.2554. Min Act: -0.1700
Data Index: 1797762 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.1617. Min Act: -0.1700
Data Index: 491946 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.0679. Min Act: -0.1700
Data Index: 6945201 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.0367. Min Act: -0.1700
Data Index: 8830264 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.0367. Min Act: -0.1700
Data Index: 957331 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.0054. Min Act: -0.1700
Data Index: 2496649 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2554. Min Range: -5.2554
Max Act: 5.0054. Min Act: -0.1700
Data Index: 3000979 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.9742. Min Act: -0.1700
Data Index: 3240283 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.9742. Min Act: -0.1700
Data Index: 684912 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.9742. Min Act: -0.1700
Data Index: 2382935 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.9429. Min Act: -0.1700
Data Index: 4446541 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.9742. Min Act: -0.1700
Data Index: 8751756 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8804. Min Act: -0.1700
Data Index: 4446540 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8804. Min Act: -0.1700
Data Index: 1641519 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.9117. Min Act: -0.1700
Data Index: 3326289 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8804. Min Act: -0.1700
Data Index: 1123354 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8492. Min Act: -0.1700
Data Index: 2382944 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8492. Min Act: -0.1700
Data Index: 5702002 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8492. Min Act: -0.1700
Data Index: 5013991 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2554. Min Range: -5.2554
Max Act: 4.8492. Min Act: -0.1700
Data Index: 5835162 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19