Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.8442. Min Act: -0.1700
Data Index: 309631 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.7192. Min Act: -0.1700
Data Index: 1091793 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.7505. Min Act: -0.1700
Data Index: 7086067 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6567. Min Act: -0.1700
Data Index: 4217340 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6567. Min Act: -0.1700
Data Index: 4376664 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6567. Min Act: -0.1700
Data Index: 483713 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6255. Min Act: -0.1700
Data Index: 3038989 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6255. Min Act: -0.1700
Data Index: 8542841 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6255. Min Act: -0.1700
Data Index: 7086066 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 8587215 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.6255. Min Act: -0.1700
Data Index: 635933 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 695133 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 6175664 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 101039 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 8644526 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 7712914 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5630. Min Act: -0.1700
Data Index: 1877799 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5630. Min Act: -0.1700
Data Index: 7712893 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5942. Min Act: -0.1700
Data Index: 2859354 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8442. Min Range: -5.8442
Max Act: 5.5630. Min Act: -0.1700
Data Index: 7288385 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19