Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1098 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0965. Min Range: -5.0965
Max Act: 5.0965. Min Act: -0.1700
Data Index: 1591524 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0965. Min Range: -5.0965
Max Act: 5.0340. Min Act: -0.1700
Data Index: 1290821 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0965. Min Range: -5.0965
Max Act: 5.0027. Min Act: -0.1700
Data Index: 2392597 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.9402. Min Act: -0.1700
Data Index: 5070199 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.9402. Min Act: -0.1700
Data Index: 4842804 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.8777. Min Act: -0.1700
Data Index: 18999 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.8777. Min Act: -0.1700
Data Index: 6852712 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.8465. Min Act: -0.1700
Data Index: 5989213 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.8152. Min Act: -0.1700
Data Index: 5892511 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7840. Min Act: -0.1700
Data Index: 458996 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7840. Min Act: -0.1700
Data Index: 2607896 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7527. Min Act: -0.1700
Data Index: 1905092 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7840. Min Act: -0.1700
Data Index: 595025 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7527. Min Act: -0.1700
Data Index: 389536 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7215. Min Act: -0.1700
Data Index: 744795 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7215. Min Act: -0.1700
Data Index: 525169 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.6902. Min Act: -0.1700
Data Index: 2720003 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.7215. Min Act: -0.1700
Data Index: 5056452 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.6902. Min Act: -0.1700
Data Index: 6372467 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0965. Min Range: -5.0965
Max Act: 4.6902. Min Act: -0.1700
Data Index: 243857 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19