Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.1876. Min Act: -0.1700
Data Index: 2711489 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.1544. Min Act: -0.1700
Data Index: 4414304 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.1377. Min Act: -0.1700
Data Index: 300262 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0539. Min Act: -0.1700
Data Index: 4729491 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0371. Min Act: -0.1700
Data Index: 6459691 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0371. Min Act: -0.1700
Data Index: 1992875 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 1815557 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 7175079 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 6088955 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 3320104 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 7724710 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 8501420 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1876. Min Range: -2.1876
Max Act: 2.0034. Min Act: -0.1700
Data Index: 2336220 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9865. Min Act: -0.1700
Data Index: 8060105 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9865. Min Act: -0.1700
Data Index: 2090676 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9695. Min Act: -0.1700
Data Index: 5280163 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9865. Min Act: -0.1700
Data Index: 8798660 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9695. Min Act: -0.1700
Data Index: 3682023 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9526. Min Act: -0.1700
Data Index: 912689 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1876. Min Range: -2.1876
Max Act: 1.9526. Min Act: -0.1700
Data Index: 855294 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19