Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.4945. Min Act: -0.1700
Data Index: 6918445 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.3382. Min Act: -0.1700
Data Index: 8162505 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.3070. Min Act: -0.1700
Data Index: 6831159 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.2132. Min Act: -0.1700
Data Index: 6554472 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.1820. Min Act: -0.1700
Data Index: 1922359 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.1507. Min Act: -0.1700
Data Index: 3990325 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.0882. Min Act: -0.1700
Data Index: 4463251 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.0882. Min Act: -0.1700
Data Index: 235613 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.1195. Min Act: -0.1700
Data Index: 3349619 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 5334255 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 3328733 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4945. Min Range: -6.4945
Max Act: 6.0257. Min Act: -0.1700
Data Index: 4939693 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 2202433 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9632. Min Act: -0.1700
Data Index: 6422449 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 3583278 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9632. Min Act: -0.1700
Data Index: 5659567 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9632. Min Act: -0.1700
Data Index: 459152 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9632. Min Act: -0.1700
Data Index: 8485821 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9320. Min Act: -0.1700
Data Index: 1205627 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4945. Min Range: -6.4945
Max Act: 5.9632. Min Act: -0.1700
Data Index: 5660922 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19