Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.9184. Min Act: -0.1700
Data Index: 3555049 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.7151. Min Act: -0.1700
Data Index: 5440174 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.6682. Min Act: -0.1700
Data Index: 7207269 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.6525. Min Act: -0.1700
Data Index: 651240 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.6213. Min Act: -0.1700
Data Index: 280963 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5900. Min Act: -0.1700
Data Index: 6692945 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5743. Min Act: -0.1700
Data Index: 5857400 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5430. Min Act: -0.1700
Data Index: 4869569 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5430. Min Act: -0.1700
Data Index: 8774266 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5430. Min Act: -0.1700
Data Index: 5650425 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5586. Min Act: -0.1700
Data Index: 5034706 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5273. Min Act: -0.1700
Data Index: 7748540 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.5273. Min Act: -0.1700
Data Index: 8519232 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4960. Min Act: -0.1700
Data Index: 3223254 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4803. Min Act: -0.1700
Data Index: 370343 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4647. Min Act: -0.1700
Data Index: 1947672 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4490. Min Act: -0.1700
Data Index: 4277366 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4490. Min Act: -0.1700
Data Index: 6620300 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4333. Min Act: -0.1700
Data Index: 7928279 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9184. Min Range: -3.9184
Max Act: 3.4490. Min Act: -0.1700
Data Index: 5809542 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19