Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2501. Min Range: -3.2501
Max Act: 3.2501. Min Act: -0.1700
Data Index: 478428 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2501. Min Range: -3.2501
Max Act: 3.0769. Min Act: -0.1700
Data Index: 5301540 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2501. Min Range: -3.2501
Max Act: 3.0612. Min Act: -0.1700
Data Index: 4416190 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2501. Min Range: -3.2501
Max Act: 3.0138. Min Act: -0.1700
Data Index: 1938286 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.9822. Min Act: -0.1700
Data Index: 5936983 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.9347. Min Act: -0.1700
Data Index: 6520667 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.9189. Min Act: -0.1700
Data Index: 6668254 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.9347. Min Act: -0.1700
Data Index: 7573629 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.9030. Min Act: -0.1700
Data Index: 7189925 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8713. Min Act: -0.1700
Data Index: 4554772 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8872. Min Act: -0.1700
Data Index: 6972956 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8395. Min Act: -0.1700
Data Index: 7546378 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8713. Min Act: -0.1700
Data Index: 4357715 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8236. Min Act: -0.1700
Data Index: 8791314 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8077. Min Act: -0.1700
Data Index: 6414685 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.8077. Min Act: -0.1700
Data Index: 1727521 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.7918. Min Act: -0.1700
Data Index: 1039500 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.7758. Min Act: -0.1700
Data Index: 3092825 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.7439. Min Act: -0.1700
Data Index: 85114 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2501. Min Range: -3.2501
Max Act: 2.7599. Min Act: -0.1700
Data Index: 371900 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19