Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1263 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.6752. Min Act: -0.1700
Data Index: 4824885 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.4877. Min Act: -0.1700
Data Index: 5358840 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.4564. Min Act: -0.1700
Data Index: 6192168 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.4252. Min Act: -0.1700
Data Index: 7232436 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.3939. Min Act: -0.1700
Data Index: 6052627 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.3627. Min Act: -0.1700
Data Index: 7328158 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.3314. Min Act: -0.1700
Data Index: 5664878 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.3314. Min Act: -0.1700
Data Index: 5719693 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.3002. Min Act: -0.1700
Data Index: 6471847 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2689. Min Act: -0.1700
Data Index: 7777137 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2377. Min Act: -0.1700
Data Index: 7923541 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2689. Min Act: -0.1700
Data Index: 8661366 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2377. Min Act: -0.1700
Data Index: 7490937 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2377. Min Act: -0.1700
Data Index: 2818491 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2064. Min Act: -0.1700
Data Index: 5581695 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2064. Min Act: -0.1700
Data Index: 2684020 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2064. Min Act: -0.1700
Data Index: 21836 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2064. Min Act: -0.1700
Data Index: 3956317 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.1752. Min Act: -0.1700
Data Index: 2015605 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6752. Min Range: -5.6752
Max Act: 5.2064. Min Act: -0.1700
Data Index: 4628704 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19