Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0105. Min Range: -5.0105
Max Act: 5.0105. Min Act: -0.1700
Data Index: 8476357 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9793. Min Act: -0.1700
Data Index: 1475759 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9793. Min Act: -0.1700
Data Index: 7943391 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9480. Min Act: -0.1700
Data Index: 2605666 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9168. Min Act: -0.1700
Data Index: 5395049 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8855. Min Act: -0.1700
Data Index: 3434707 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9168. Min Act: -0.1700
Data Index: 714071 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9168. Min Act: -0.1700
Data Index: 2361047 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.9168. Min Act: -0.1700
Data Index: 6932282 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8855. Min Act: -0.1700
Data Index: 3939842 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8855. Min Act: -0.1700
Data Index: 8283342 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8855. Min Act: -0.1700
Data Index: 4673186 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8543. Min Act: -0.1700
Data Index: 2521546 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8543. Min Act: -0.1700
Data Index: 3939844 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8543. Min Act: -0.1700
Data Index: 7265039 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8230. Min Act: -0.1700
Data Index: 2870834 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8230. Min Act: -0.1700
Data Index: 6752437 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8230. Min Act: -0.1700
Data Index: 504175 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8230. Min Act: -0.1700
Data Index: 2445265 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0105. Min Range: -5.0105
Max Act: 4.8230. Min Act: -0.1700
Data Index: 8331155 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19