Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.5337. Min Act: -0.1700
Data Index: 7497660 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.3775. Min Act: -0.1700
Data Index: 7546969 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2837. Min Act: -0.1700
Data Index: 447361 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2837. Min Act: -0.1700
Data Index: 5112532 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.3150. Min Act: -0.1700
Data Index: 7174428 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2525. Min Act: -0.1700
Data Index: 5747820 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2525. Min Act: -0.1700
Data Index: 233640 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2525. Min Act: -0.1700
Data Index: 3112826 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2525. Min Act: -0.1700
Data Index: 7136996 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2212. Min Act: -0.1700
Data Index: 850949 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.2212. Min Act: -0.1700
Data Index: 249992 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1900. Min Act: -0.1700
Data Index: 1666293 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1900. Min Act: -0.1700
Data Index: 3071944 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1900. Min Act: -0.1700
Data Index: 8020309 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1900. Min Act: -0.1700
Data Index: 3144565 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1587. Min Act: -0.1700
Data Index: 4928105 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1587. Min Act: -0.1700
Data Index: 7601037 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1275. Min Act: -0.1700
Data Index: 7274898 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5601022 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5337. Min Range: -5.5337
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5139800 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19