Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1693. Min Range: -6.1693
Max Act: 6.1693. Min Act: -0.1700
Data Index: 5902339 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.9505. Min Act: -0.1700
Data Index: 2542412 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.8255. Min Act: -0.1700
Data Index: 4744964 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.7005. Min Act: -0.1700
Data Index: 5087943 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.7005. Min Act: -0.1700
Data Index: 3987450 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.6693. Min Act: -0.1700
Data Index: 6263762 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.6380. Min Act: -0.1700
Data Index: 4323091 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.6068. Min Act: -0.1700
Data Index: 4489345 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.5755. Min Act: -0.1700
Data Index: 4045467 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.6068. Min Act: -0.1700
Data Index: 1600262 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.6068. Min Act: -0.1700
Data Index: 4744966 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.5443. Min Act: -0.1700
Data Index: 4816046 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.5443. Min Act: -0.1700
Data Index: 6263765 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.5130. Min Act: -0.1700
Data Index: 6545508 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.5130. Min Act: -0.1700
Data Index: 4744965 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.5130. Min Act: -0.1700
Data Index: 5899779 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.4818. Min Act: -0.1700
Data Index: 7389652 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.4818. Min Act: -0.1700
Data Index: 7649906 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.4505. Min Act: -0.1700
Data Index: 5607391 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1693. Min Range: -6.1693
Max Act: 5.4505. Min Act: -0.1700
Data Index: 2783246 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19