Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1160 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0156. Min Range: -4.0156
Max Act: 4.0156. Min Act: -0.1700
Data Index: 1780328 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0156. Min Range: -4.0156
Max Act: 4.0156. Min Act: -0.1700
Data Index: 4437499 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9844. Min Act: -0.1700
Data Index: 5939149 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9844. Min Act: -0.1700
Data Index: 3433964 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9844. Min Act: -0.1700
Data Index: 6802568 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9531. Min Act: -0.1700
Data Index: 6180835 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9531. Min Act: -0.1700
Data Index: 884204 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9531. Min Act: -0.1700
Data Index: 5230053 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9531. Min Act: -0.1700
Data Index: 4551217 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9531. Min Act: -0.1700
Data Index: 2309225 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9218. Min Act: -0.1700
Data Index: 1102289 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.9218. Min Act: -0.1700
Data Index: 2255777 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8906. Min Act: -0.1700
Data Index: 8739540 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8906. Min Act: -0.1700
Data Index: 6140528 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8906. Min Act: -0.1700
Data Index: 5889588 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8906. Min Act: -0.1700
Data Index: 7995765 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8906. Min Act: -0.1700
Data Index: 6382148 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8906. Min Act: -0.1700
Data Index: 848846 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8593. Min Act: -0.1700
Data Index: 572767 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0156. Min Range: -4.0156
Max Act: 3.8280. Min Act: -0.1700
Data Index: 7489501 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19