Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.4939. Min Act: -0.1700
Data Index: 7262867 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.4314. Min Act: -0.1700
Data Index: 5265173 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.4001. Min Act: -0.1700
Data Index: 4017911 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.3064. Min Act: -0.1700
Data Index: 2166905 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.3064. Min Act: -0.1700
Data Index: 1602436 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.2439. Min Act: -0.1700
Data Index: 3628360 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.3064. Min Act: -0.1700
Data Index: 409648 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.2126. Min Act: -0.1700
Data Index: 1407161 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.2126. Min Act: -0.1700
Data Index: 7553773 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.2126. Min Act: -0.1700
Data Index: 879340 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1814. Min Act: -0.1700
Data Index: 5485815 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1814. Min Act: -0.1700
Data Index: 6767939 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1501. Min Act: -0.1700
Data Index: 5625074 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1814. Min Act: -0.1700
Data Index: 5303860 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1814. Min Act: -0.1700
Data Index: 2530940 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1501. Min Act: -0.1700
Data Index: 7482963 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1814. Min Act: -0.1700
Data Index: 7463579 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1501. Min Act: -0.1700
Data Index: 6072614 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1189. Min Act: -0.1700
Data Index: 361203 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4939. Min Range: -6.4939
Max Act: 6.1501. Min Act: -0.1700
Data Index: 83981 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19