Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.5207. Min Act: -0.1700
Data Index: 1106031 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.4270. Min Act: -0.1700
Data Index: 8268308 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.2082. Min Act: -0.1700
Data Index: 4340878 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.1457. Min Act: -0.1700
Data Index: 4622577 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.1145. Min Act: -0.1700
Data Index: 4138007 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.1145. Min Act: -0.1700
Data Index: 4485979 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.1145. Min Act: -0.1700
Data Index: 4340883 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.1145. Min Act: -0.1700
Data Index: 4194205 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0832. Min Act: -0.1700
Data Index: 6494481 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0832. Min Act: -0.1700
Data Index: 6280265 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.1145. Min Act: -0.1700
Data Index: 8701376 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0832. Min Act: -0.1700
Data Index: 3520677 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0832. Min Act: -0.1700
Data Index: 2304534 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0832. Min Act: -0.1700
Data Index: 7160832 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0520. Min Act: -0.1700
Data Index: 8755115 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0520. Min Act: -0.1700
Data Index: 8186037 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5207. Min Range: -6.5207
Max Act: 6.0207. Min Act: -0.1700
Data Index: 6806084 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5207. Min Range: -6.5207
Max Act: 5.9895. Min Act: -0.1700
Data Index: 5083567 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5207. Min Range: -6.5207
Max Act: 5.9582. Min Act: -0.1700
Data Index: 5186844 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5207. Min Range: -6.5207
Max Act: 5.9582. Min Act: -0.1700
Data Index: 1470565 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19