Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2252 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0105. Min Range: -8.0105
Max Act: 8.0105. Min Act: -0.1700
Data Index: 8283046 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.9480. Min Act: -0.1700
Data Index: 226244 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.9480. Min Act: -0.1700
Data Index: 4573970 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.8230. Min Act: -0.1700
Data Index: 5442035 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.7918. Min Act: -0.1700
Data Index: 808757 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.7293. Min Act: -0.1700
Data Index: 2365747 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.7293. Min Act: -0.1700
Data Index: 3843053 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6980. Min Act: -0.1700
Data Index: 2026204 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6980. Min Act: -0.1700
Data Index: 8461151 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6668. Min Act: -0.1700
Data Index: 3364752 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6668. Min Act: -0.1700
Data Index: 3201175 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6668. Min Act: -0.1700
Data Index: 3921511 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6043. Min Act: -0.1700
Data Index: 6071271 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.6043. Min Act: -0.1700
Data Index: 651388 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.5730. Min Act: -0.1700
Data Index: 4609279 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.5418. Min Act: -0.1700
Data Index: 4758310 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.5105. Min Act: -0.1700
Data Index: 5823527 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4677063 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.4793. Min Act: -0.1700
Data Index: 2902374 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0105. Min Range: -8.0105
Max Act: 7.4793. Min Act: -0.1700
Data Index: 8521630 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19