Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.8932. Min Act: -0.1700
Data Index: 4309013 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.8307. Min Act: -0.1700
Data Index: 5806285 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.8307. Min Act: -0.1700
Data Index: 4270491 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.8307. Min Act: -0.1700
Data Index: 4261684 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7994. Min Act: -0.1700
Data Index: 2904747 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7681. Min Act: -0.1700
Data Index: 5806286 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7368. Min Act: -0.1700
Data Index: 683785 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7368. Min Act: -0.1700
Data Index: 8089565 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7368. Min Act: -0.1700
Data Index: 5758496 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7368. Min Act: -0.1700
Data Index: 6808079 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 7763356 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 7719644 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 5260482 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 4092186 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 455290 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6899. Min Act: -0.1700
Data Index: 3746682 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6899. Min Act: -0.1700
Data Index: 7942731 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.7056. Min Act: -0.1700
Data Index: 8287379 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 6291959 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8932. Min Range: -3.8932
Max Act: 3.6743. Min Act: -0.1700
Data Index: 4687900 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19