Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4630 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.4055. Min Act: -0.1700
Data Index: 4616941 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.4680. Min Act: -0.1700
Data Index: 8489137 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.4680. Min Act: -0.1700
Data Index: 3447428 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.2805. Min Act: -0.1700
Data Index: 6802757 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 2616097 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 2709528 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0930. Min Act: -0.1700
Data Index: 2787809 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.1555. Min Act: -0.1700
Data Index: 8493454 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.1555. Min Act: -0.1700
Data Index: 1645653 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0930. Min Act: -0.1700
Data Index: 2164054 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0930. Min Act: -0.1700
Data Index: 2289 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0930. Min Act: -0.1700
Data Index: 1685360 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0305. Min Act: -0.1700
Data Index: 7181025 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0305. Min Act: -0.1700
Data Index: 1844122 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0305. Min Act: -0.1700
Data Index: 70697 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4680. Min Range: -8.4680
Max Act: 8.0305. Min Act: -0.1700
Data Index: 8483066 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4680. Min Range: -8.4680
Max Act: 7.9992. Min Act: -0.1700
Data Index: 6737766 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4680. Min Range: -8.4680
Max Act: 7.9992. Min Act: -0.1700
Data Index: 4813143 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4680. Min Range: -8.4680
Max Act: 7.9992. Min Act: -0.1700
Data Index: 2385384 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4680. Min Range: -8.4680
Max Act: 7.9992. Min Act: -0.1700
Data Index: 7400575 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19