Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4232 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.7470. Min Range: -19.7470
Max Act: 19.7470. Min Act: -0.1700
Data Index: 1216163 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.7470. Min Range: -19.7470
Max Act: 19.2470. Min Act: -0.1700
Data Index: 6089668 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.7470. Min Range: -19.7470
Max Act: 19.1220. Min Act: -0.1700
Data Index: 6608724 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.7470. Min Range: -19.7470
Max Act: 19.1220. Min Act: -0.1700
Data Index: 4803523 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.9970. Min Act: -0.1700
Data Index: 3183618 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.9970. Min Act: -0.1700
Data Index: 5301866 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.7470. Min Act: -0.1700
Data Index: 4423650 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.7470. Min Act: -0.1700
Data Index: 2221064 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.7470. Min Act: -0.1700
Data Index: 8600130 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.7470. Min Act: -0.1700
Data Index: 8404186 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.7470. Min Act: -0.1700
Data Index: 2641142 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.6220. Min Act: -0.1700
Data Index: 8809952 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.6220. Min Act: -0.1700
Data Index: 2315530 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.4970. Min Act: -0.1700
Data Index: 4124578 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.4970. Min Act: -0.1700
Data Index: 7112420 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.4970. Min Act: -0.1700
Data Index: 206626 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.3720. Min Act: -0.1700
Data Index: 662281 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.3720. Min Act: -0.1700
Data Index: 4935033 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.3720. Min Act: -0.1700
Data Index: 3086197 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.7470. Min Range: -19.7470
Max Act: 18.3720. Min Act: -0.1700
Data Index: 7895433 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19