Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2645. Min Range: -6.2645
Max Act: 6.2645. Min Act: -0.1700
Data Index: 8358931 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2645. Min Range: -6.2645
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4144713 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2645. Min Range: -6.2645
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4362387 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2645. Min Range: -6.2645
Max Act: 6.1708. Min Act: -0.1700
Data Index: 5147284 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2645. Min Range: -6.2645
Max Act: 6.0770. Min Act: -0.1700
Data Index: 4803937 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2645. Min Range: -6.2645
Max Act: 6.1083. Min Act: -0.1700
Data Index: 4362386 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9833. Min Act: -0.1700
Data Index: 3429289 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9833. Min Act: -0.1700
Data Index: 7503149 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9833. Min Act: -0.1700
Data Index: 4443681 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9520. Min Act: -0.1700
Data Index: 1230159 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9208. Min Act: -0.1700
Data Index: 1708620 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9208. Min Act: -0.1700
Data Index: 5956982 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9208. Min Act: -0.1700
Data Index: 2824126 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9208. Min Act: -0.1700
Data Index: 6164860 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9208. Min Act: -0.1700
Data Index: 4333090 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.9208. Min Act: -0.1700
Data Index: 583932 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.8895. Min Act: -0.1700
Data Index: 7236163 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.8895. Min Act: -0.1700
Data Index: 5912291 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.8895. Min Act: -0.1700
Data Index: 5456228 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2645. Min Range: -6.2645
Max Act: 5.8895. Min Act: -0.1700
Data Index: 1596650 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19