Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.3489. Min Act: -0.1700
Data Index: 7921340 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.2864. Min Act: -0.1700
Data Index: 2765376 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.2552. Min Act: -0.1700
Data Index: 1670304 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.2552. Min Act: -0.1700
Data Index: 1670308 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1927. Min Act: -0.1700
Data Index: 3585998 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1927. Min Act: -0.1700
Data Index: 1694684 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1927. Min Act: -0.1700
Data Index: 5991729 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1927. Min Act: -0.1700
Data Index: 1670301 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1614. Min Act: -0.1700
Data Index: 2286661 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1614. Min Act: -0.1700
Data Index: 7079725 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1614. Min Act: -0.1700
Data Index: 960640 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1927. Min Act: -0.1700
Data Index: 1670299 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.0989. Min Act: -0.1700
Data Index: 487263 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1302. Min Act: -0.1700
Data Index: 2989557 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2989570 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1302. Min Act: -0.1700
Data Index: 3585978 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1302. Min Act: -0.1700
Data Index: 8261763 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1302. Min Act: -0.1700
Data Index: 1670309 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1302. Min Act: -0.1700
Data Index: 4660977 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3489. Min Range: -6.3489
Max Act: 6.1302. Min Act: -0.1700
Data Index: 582430 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19