Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4487 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.7470. Min Act: -0.1700
Data Index: 7284591 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.7470. Min Act: -0.1700
Data Index: 2809093 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.7158. Min Act: -0.1700
Data Index: 4275274 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.6845. Min Act: -0.1700
Data Index: 5320810 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.6220. Min Act: -0.1700
Data Index: 4368049 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.5595. Min Act: -0.1700
Data Index: 1470816 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.5595. Min Act: -0.1700
Data Index: 326292 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.5595. Min Act: -0.1700
Data Index: 8293833 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.5283. Min Act: -0.1700
Data Index: 6634704 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4970. Min Act: -0.1700
Data Index: 82006 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4658. Min Act: -0.1700
Data Index: 6799226 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.5283. Min Act: -0.1700
Data Index: 1850467 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4658. Min Act: -0.1700
Data Index: 7914142 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4970. Min Act: -0.1700
Data Index: 5746193 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4345. Min Act: -0.1700
Data Index: 77842 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4658. Min Act: -0.1700
Data Index: 6895026 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3007219 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5160787 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4345. Min Act: -0.1700
Data Index: 4423942 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7470. Min Range: -5.7470
Max Act: 5.4345. Min Act: -0.1700
Data Index: 4956875 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19