Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 624 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.8964. Min Act: -0.1700
Data Index: 3004952 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.8026. Min Act: -0.1700
Data Index: 6911773 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5526. Min Act: -0.1700
Data Index: 6595609 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5214. Min Act: -0.1700
Data Index: 5443797 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4901. Min Act: -0.1700
Data Index: 7103747 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4901. Min Act: -0.1700
Data Index: 8501467 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4589. Min Act: -0.1700
Data Index: 8365821 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4589. Min Act: -0.1700
Data Index: 1959545 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4276. Min Act: -0.1700
Data Index: 8629974 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4276. Min Act: -0.1700
Data Index: 7012539 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.3964. Min Act: -0.1700
Data Index: 2117678 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.3651. Min Act: -0.1700
Data Index: 5394907 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.3651. Min Act: -0.1700
Data Index: 5062251 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.3651. Min Act: -0.1700
Data Index: 1549924 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.3026. Min Act: -0.1700
Data Index: 4765117 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.2401. Min Act: -0.1700
Data Index: 1357320 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.2401. Min Act: -0.1700
Data Index: 362923 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.2714. Min Act: -0.1700
Data Index: 817049 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.2714. Min Act: -0.1700
Data Index: 5964625 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.2714. Min Act: -0.1700
Data Index: 6322735 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19