Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4315 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0494. Min Range: -3.0494
Max Act: 3.0494. Min Act: -0.1700
Data Index: 3890946 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0494. Min Range: -3.0494
Max Act: 3.0178. Min Act: -0.1700
Data Index: 8733679 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0494. Min Range: -3.0494
Max Act: 3.0020. Min Act: -0.1700
Data Index: 42042 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9704. Min Act: -0.1700
Data Index: 2117626 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9545. Min Act: -0.1700
Data Index: 1490636 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9387. Min Act: -0.1700
Data Index: 1710210 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9387. Min Act: -0.1700
Data Index: 1464775 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9229. Min Act: -0.1700
Data Index: 5333669 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9070. Min Act: -0.1700
Data Index: 4543292 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.9070. Min Act: -0.1700
Data Index: 5271479 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8912. Min Act: -0.1700
Data Index: 2799772 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8753. Min Act: -0.1700
Data Index: 3685354 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8753. Min Act: -0.1700
Data Index: 4455705 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8753. Min Act: -0.1700
Data Index: 2116230 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8753. Min Act: -0.1700
Data Index: 5581708 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8753. Min Act: -0.1700
Data Index: 4601266 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8594. Min Act: -0.1700
Data Index: 6052400 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8594. Min Act: -0.1700
Data Index: 6833685 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8435. Min Act: -0.1700
Data Index: 2305616 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0494. Min Range: -3.0494
Max Act: 2.8435. Min Act: -0.1700
Data Index: 3563825 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19