Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5333 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.1271. Min Act: -0.1700
Data Index: 4895836 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.1271. Min Act: -0.1700
Data Index: 5885148 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8636270 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0646. Min Act: -0.1700
Data Index: 40038 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0646. Min Act: -0.1700
Data Index: 792288 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0333. Min Act: -0.1700
Data Index: 3731130 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0333. Min Act: -0.1700
Data Index: 988079 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 3314756 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 2827221 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 2861210 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 7733911 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1271. Min Range: -5.1271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 6284425 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 8227591 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 4961351 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 6095409 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 6240662 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 4771506 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9396. Min Act: -0.1700
Data Index: 5226690 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9396. Min Act: -0.1700
Data Index: 8832283 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1271. Min Range: -5.1271
Max Act: 4.9396. Min Act: -0.1700
Data Index: 6362018 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19