Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4888 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.4526. Min Act: -0.1700
Data Index: 7253939 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.3901. Min Act: -0.1700
Data Index: 3928515 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.3588. Min Act: -0.1700
Data Index: 4575328 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2963. Min Act: -0.1700
Data Index: 5810167 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2963. Min Act: -0.1700
Data Index: 7319485 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2248780 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2789194 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 6069373 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 8220089 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2338. Min Act: -0.1700
Data Index: 518924 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2025. Min Act: -0.1700
Data Index: 5488231 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2025. Min Act: -0.1700
Data Index: 2791155 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.2025. Min Act: -0.1700
Data Index: 3691572 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1400. Min Act: -0.1700
Data Index: 7788101 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1713. Min Act: -0.1700
Data Index: 7380281 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1713. Min Act: -0.1700
Data Index: 6910782 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1400. Min Act: -0.1700
Data Index: 5318312 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1400. Min Act: -0.1700
Data Index: 3104542 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1400. Min Act: -0.1700
Data Index: 1147760 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4526. Min Range: -4.4526
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2042515 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19