Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 114 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.2103. Min Act: -0.1700
Data Index: 8167230 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.1791. Min Act: -0.1700
Data Index: 8729377 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.1791. Min Act: -0.1700
Data Index: 2473520 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.1166. Min Act: -0.1700
Data Index: 4873207 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0853. Min Act: -0.1700
Data Index: 8280779 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0853. Min Act: -0.1700
Data Index: 8368165 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0540. Min Act: -0.1700
Data Index: 2982460 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0540. Min Act: -0.1700
Data Index: 3399389 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0228. Min Act: -0.1700
Data Index: 3371146 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0228. Min Act: -0.1700
Data Index: 3377143 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9915. Min Act: -0.1700
Data Index: 1560830 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9915. Min Act: -0.1700
Data Index: 8490538 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9915. Min Act: -0.1700
Data Index: 1487641 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2103. Min Range: -4.2103
Max Act: 4.0228. Min Act: -0.1700
Data Index: 5296428 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9915. Min Act: -0.1700
Data Index: 8398505 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9915. Min Act: -0.1700
Data Index: 1358181 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9603. Min Act: -0.1700
Data Index: 2738182 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9915. Min Act: -0.1700
Data Index: 7252158 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9290. Min Act: -0.1700
Data Index: 5778416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2103. Min Range: -4.2103
Max Act: 3.9603. Min Act: -0.1700
Data Index: 5815518 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19