Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.1599. Min Act: -0.1700
Data Index: 8687312 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.0662. Min Act: -0.1700
Data Index: 8023399 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.0662. Min Act: -0.1700
Data Index: 7835678 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9412. Min Act: -0.1700
Data Index: 4107224 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9412. Min Act: -0.1700
Data Index: 1289232 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8787. Min Act: -0.1700
Data Index: 7381618 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8787. Min Act: -0.1700
Data Index: 738424 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8787. Min Act: -0.1700
Data Index: 1732115 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8474. Min Act: -0.1700
Data Index: 515440 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8162. Min Act: -0.1700
Data Index: 1761507 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 4078010 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 3618211 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 361823 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7224. Min Act: -0.1700
Data Index: 531163 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7537. Min Act: -0.1700
Data Index: 7005681 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7224. Min Act: -0.1700
Data Index: 1221004 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7224. Min Act: -0.1700
Data Index: 5292409 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.6912. Min Act: -0.1700
Data Index: 6019951 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.6912. Min Act: -0.1700
Data Index: 3057560 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.6912. Min Act: -0.1700
Data Index: 2947153 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19