Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 673 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.8655. Min Act: -0.1700
Data Index: 3402397 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.7718. Min Act: -0.1700
Data Index: 4307954 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.7718. Min Act: -0.1700
Data Index: 1088140 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.5530. Min Act: -0.1700
Data Index: 5749692 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.4280. Min Act: -0.1700
Data Index: 3049216 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3968. Min Act: -0.1700
Data Index: 553245 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3655. Min Act: -0.1700
Data Index: 8126631 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3655. Min Act: -0.1700
Data Index: 4091970 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3655. Min Act: -0.1700
Data Index: 7828096 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3655. Min Act: -0.1700
Data Index: 7762275 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3343. Min Act: -0.1700
Data Index: 2663901 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3343. Min Act: -0.1700
Data Index: 98885 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3030. Min Act: -0.1700
Data Index: 8036150 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.3343. Min Act: -0.1700
Data Index: 1815009 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.2718. Min Act: -0.1700
Data Index: 6672953 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.2718. Min Act: -0.1700
Data Index: 3168377 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.2718. Min Act: -0.1700
Data Index: 8494393 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.2093. Min Act: -0.1700
Data Index: 2426200 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.1780. Min Act: -0.1700
Data Index: 1674840 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8655. Min Range: -4.8655
Max Act: 4.2093. Min Act: -0.1700
Data Index: 4347351 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19