Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.7445. Min Act: -0.1700
Data Index: 4773147 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5258. Min Act: -0.1700
Data Index: 4141352 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.3695. Min Act: -0.1700
Data Index: 464874 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.3070. Min Act: -0.1700
Data Index: 3240498 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.3070. Min Act: -0.1700
Data Index: 4665383 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.3070. Min Act: -0.1700
Data Index: 203302 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2757. Min Act: -0.1700
Data Index: 5421594 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2757. Min Act: -0.1700
Data Index: 3288433 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2757. Min Act: -0.1700
Data Index: 2794494 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2445. Min Act: -0.1700
Data Index: 8226196 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2445. Min Act: -0.1700
Data Index: 692290 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2132. Min Act: -0.1700
Data Index: 3998841 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.2132. Min Act: -0.1700
Data Index: 5921725 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1820. Min Act: -0.1700
Data Index: 3359138 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1820. Min Act: -0.1700
Data Index: 4217411 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1820. Min Act: -0.1700
Data Index: 8081053 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1820. Min Act: -0.1700
Data Index: 3019933 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1507. Min Act: -0.1700
Data Index: 3601886 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1507. Min Act: -0.1700
Data Index: 5469581 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.1507. Min Act: -0.1700
Data Index: 3144148 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19