Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.5489. Min Act: -0.1700
Data Index: 595656 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.5489. Min Act: -0.1700
Data Index: 3032790 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.3614. Min Act: -0.1700
Data Index: 6363578 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.3927. Min Act: -0.1700
Data Index: 935366 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.3302. Min Act: -0.1700
Data Index: 4197771 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.3302. Min Act: -0.1700
Data Index: 17749 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.3302. Min Act: -0.1700
Data Index: 1112864 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2989. Min Act: -0.1700
Data Index: 6636983 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2989. Min Act: -0.1700
Data Index: 1589995 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2989. Min Act: -0.1700
Data Index: 1496783 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2677. Min Act: -0.1700
Data Index: 3741427 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2677. Min Act: -0.1700
Data Index: 6822546 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2677. Min Act: -0.1700
Data Index: 3842016 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2677. Min Act: -0.1700
Data Index: 1509562 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2364. Min Act: -0.1700
Data Index: 5750161 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2364. Min Act: -0.1700
Data Index: 2611146 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2052. Min Act: -0.1700
Data Index: 5785734 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2052. Min Act: -0.1700
Data Index: 2867654 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2052. Min Act: -0.1700
Data Index: 1909687 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5489. Min Range: -5.5489
Max Act: 5.2052. Min Act: -0.1700
Data Index: 2225862 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19