Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.3578. Min Act: -0.1700
Data Index: 182255 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.1991. Min Act: -0.1696
Data Index: 3753120 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.1287. Min Act: -0.1699
Data Index: 8703829 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.0762. Min Act: -0.1700
Data Index: 4987056 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.0238. Min Act: -0.1700
Data Index: 3377026 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.0064. Min Act: -0.1673
Data Index: 4342153 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3578. Min Range: -1.3578
Max Act: 1.0238. Min Act: -0.1700
Data Index: 994018 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9891. Min Act: -0.1700
Data Index: 5679343 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9373. Min Act: -0.1700
Data Index: 1095408 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9373. Min Act: -0.1700
Data Index: 7076669 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9201. Min Act: -0.1700
Data Index: 618584 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9373. Min Act: -0.1700
Data Index: 8018923 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9201. Min Act: -0.1700
Data Index: 3801234 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9201. Min Act: -0.1700
Data Index: 3220293 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9029. Min Act: -0.1700
Data Index: 5126968 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9029. Min Act: -0.1700
Data Index: 8018925 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.9029. Min Act: -0.1700
Data Index: 7412164 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.8773. Min Act: -0.1699
Data Index: 7197803 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.8773. Min Act: -0.1696
Data Index: 1098040 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3578. Min Range: -1.3578
Max Act: 0.8603. Min Act: -0.1700
Data Index: 880760 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19