Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1210 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1453. Min Range: -7.1453
Max Act: 7.1453. Min Act: -0.1700
Data Index: 164004 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1453. Min Range: -7.1453
Max Act: 7.0515. Min Act: -0.1700
Data Index: 3343521 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1453. Min Range: -7.1453
Max Act: 7.0203. Min Act: -0.1700
Data Index: 8362152 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.9890. Min Act: -0.1700
Data Index: 7208441 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.9578. Min Act: -0.1700
Data Index: 3518394 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.9578. Min Act: -0.1700
Data Index: 5658591 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.9265. Min Act: -0.1700
Data Index: 7114209 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.8328. Min Act: -0.1700
Data Index: 6393117 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.8328. Min Act: -0.1700
Data Index: 8824772 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.8015. Min Act: -0.1700
Data Index: 2335834 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.8015. Min Act: -0.1700
Data Index: 403353 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.8015. Min Act: -0.1700
Data Index: 2387814 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7703. Min Act: -0.1700
Data Index: 1724979 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7390. Min Act: -0.1700
Data Index: 853999 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7078. Min Act: -0.1700
Data Index: 5282938 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7078. Min Act: -0.1700
Data Index: 6814167 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7078. Min Act: -0.1700
Data Index: 4916393 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7078. Min Act: -0.1700
Data Index: 2516240 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.7078. Min Act: -0.1700
Data Index: 5269086 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1453. Min Range: -7.1453
Max Act: 6.6453. Min Act: -0.1700
Data Index: 486001 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19