Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.7725. Min Act: -0.1700
Data Index: 1439913 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.8350. Min Act: -0.1700
Data Index: 7874351 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.5850. Min Act: -0.1700
Data Index: 657025 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.6475. Min Act: -0.1700
Data Index: 4029268 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.5850. Min Act: -0.1700
Data Index: 4842945 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.4600. Min Act: -0.1700
Data Index: 3103899 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.5225. Min Act: -0.1700
Data Index: 8015019 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.3350. Min Act: -0.1700
Data Index: 6071176 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.2725. Min Act: -0.1700
Data Index: 1576165 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.2100. Min Act: -0.1700
Data Index: 7438248 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.1475. Min Act: -0.1700
Data Index: 7519964 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.1475. Min Act: -0.1700
Data Index: 1540213 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.1475. Min Act: -0.1700
Data Index: 4656735 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.0850. Min Act: -0.1700
Data Index: 3129961 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.0850. Min Act: -0.1700
Data Index: 2384086 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.0850. Min Act: -0.1700
Data Index: 8064544 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.0225. Min Act: -0.1700
Data Index: 5177258 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.0225. Min Act: -0.1700
Data Index: 7303422 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8350. Min Range: -9.8350
Max Act: 9.0225. Min Act: -0.1700
Data Index: 5425036 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8350. Min Range: -9.8350
Max Act: 8.8975. Min Act: -0.1700
Data Index: 6190361 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19