Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0622. Min Range: -10.0622
Max Act: 10.0622. Min Act: -0.1700
Data Index: 5962183 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0622. Min Range: -10.0622
Max Act: 9.5622. Min Act: -0.1700
Data Index: 7013706 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0622. Min Range: -10.0622
Max Act: 9.0622. Min Act: -0.1700
Data Index: 6212515 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0622. Min Range: -10.0622
Max Act: 9.0622. Min Act: -0.1699
Data Index: 7390840 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.9997. Min Act: -0.1700
Data Index: 3750951 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.9997. Min Act: -0.1700
Data Index: 691258 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.9997. Min Act: -0.1699
Data Index: 7390839 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.9372. Min Act: -0.1699
Data Index: 7578589 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.8747. Min Act: -0.1700
Data Index: 8459727 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.8747. Min Act: -0.1695
Data Index: 3793077 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.8747. Min Act: -0.1700
Data Index: 2939540 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.8122. Min Act: -0.1700
Data Index: 4629858 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.8122. Min Act: -0.1700
Data Index: 6037906 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.7810. Min Act: -0.1700
Data Index: 3273299 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.7810. Min Act: -0.1700
Data Index: 3482635 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.7497. Min Act: -0.1700
Data Index: 5604170 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.7497. Min Act: -0.1699
Data Index: 2134892 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.7185. Min Act: -0.1700
Data Index: 1104636 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.6872. Min Act: -0.1698
Data Index: 4650242 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0622. Min Range: -10.0622
Max Act: 8.6247. Min Act: -0.1699
Data Index: 5674109 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19