Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1754 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.6037. Min Act: -0.1700
Data Index: 4000841 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.2287. Min Act: -0.1700
Data Index: 6755308 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.2287. Min Act: -0.1700
Data Index: 7226190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.0725. Min Act: -0.1700
Data Index: 2701806 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.0725. Min Act: -0.1700
Data Index: 3339285 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.0100. Min Act: -0.1700
Data Index: 1893313 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6037. Min Range: -8.6037
Max Act: 8.0100. Min Act: -0.1700
Data Index: 625108 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.9475. Min Act: -0.1700
Data Index: 3644472 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.6975. Min Act: -0.1700
Data Index: 7251477 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.7287. Min Act: -0.1700
Data Index: 3784022 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.6975. Min Act: -0.1700
Data Index: 6942651 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.6350. Min Act: -0.1700
Data Index: 2522579 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.6037. Min Act: -0.1700
Data Index: 8144574 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.6350. Min Act: -0.1700
Data Index: 803516 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.5725. Min Act: -0.1700
Data Index: 479715 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.5412. Min Act: -0.1700
Data Index: 256618 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.5100. Min Act: -0.1700
Data Index: 5042067 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.4787. Min Act: -0.1700
Data Index: 3769421 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.4787. Min Act: -0.1700
Data Index: 7059484 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6037. Min Range: -8.6037
Max Act: 7.4787. Min Act: -0.1700
Data Index: 895375 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19