Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1903 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.4774. Min Act: -0.1700
Data Index: 8778210 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.2899. Min Act: -0.1700
Data Index: 7599965 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.2899. Min Act: -0.1700
Data Index: 6405535 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.2274. Min Act: -0.1700
Data Index: 7577342 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1962. Min Act: -0.1700
Data Index: 400772 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1962. Min Act: -0.1700
Data Index: 4377054 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1962. Min Act: -0.1700
Data Index: 153042 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1337. Min Act: -0.1700
Data Index: 3704560 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1337. Min Act: -0.1700
Data Index: 3602317 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1024. Min Act: -0.1700
Data Index: 8022537 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.1024. Min Act: -0.1700
Data Index: 3140323 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.0712. Min Act: -0.1700
Data Index: 5475701 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.0399. Min Act: -0.1700
Data Index: 5424431 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4774. Min Range: -6.4774
Max Act: 6.0087. Min Act: -0.1700
Data Index: 8022538 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4774. Min Range: -6.4774
Max Act: 5.9774. Min Act: -0.1700
Data Index: 754412 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4774. Min Range: -6.4774
Max Act: 5.9774. Min Act: -0.1700
Data Index: 3413672 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4774. Min Range: -6.4774
Max Act: 5.9774. Min Act: -0.1700
Data Index: 7696889 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4774. Min Range: -6.4774
Max Act: 5.9462. Min Act: -0.1700
Data Index: 2308218 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4774. Min Range: -6.4774
Max Act: 5.9462. Min Act: -0.1700
Data Index: 7642230 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4774. Min Range: -6.4774
Max Act: 5.9462. Min Act: -0.1700
Data Index: 2634500 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19