Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4457 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.5480. Min Act: -0.1700
Data Index: 6255568 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.3605. Min Act: -0.1700
Data Index: 1419225 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.1730. Min Act: -0.1700
Data Index: 4581711 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.1105. Min Act: -0.1700
Data Index: 2206884 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.1105. Min Act: -0.1700
Data Index: 3459766 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.1105. Min Act: -0.1700
Data Index: 4097868 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.0480. Min Act: -0.1700
Data Index: 3505267 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.1105. Min Act: -0.1700
Data Index: 426362 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.0480. Min Act: -0.1700
Data Index: 608116 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.0480. Min Act: -0.1700
Data Index: 1535707 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.0480. Min Act: -0.1700
Data Index: 8346640 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.0480. Min Act: -0.1700
Data Index: 8235044 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5480. Min Range: -8.5480
Max Act: 8.0480. Min Act: -0.1700
Data Index: 7118970 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9230. Min Act: -0.1700
Data Index: 3854915 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9855. Min Act: -0.1700
Data Index: 7687872 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9855. Min Act: -0.1700
Data Index: 6813239 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9855. Min Act: -0.1700
Data Index: 5913646 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9855. Min Act: -0.1700
Data Index: 309162 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9855. Min Act: -0.1700
Data Index: 1627175 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5480. Min Range: -8.5480
Max Act: 7.9855. Min Act: -0.1700
Data Index: 8734560 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19