Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.6686. Min Act: -0.1700
Data Index: 7319139 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.4811. Min Act: -0.1700
Data Index: 2976628 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.4811. Min Act: -0.1700
Data Index: 4328477 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.4186. Min Act: -0.1700
Data Index: 4514844 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3874. Min Act: -0.1700
Data Index: 5579282 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3874. Min Act: -0.1700
Data Index: 87530 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3874. Min Act: -0.1700
Data Index: 1008104 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3874. Min Act: -0.1700
Data Index: 3963728 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3249. Min Act: -0.1700
Data Index: 2135850 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3561. Min Act: -0.1700
Data Index: 5757875 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.3249. Min Act: -0.1700
Data Index: 6649774 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 8015424 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 8145431 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 534382 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 3564778 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 3290532 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 2463793 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2936. Min Act: -0.1700
Data Index: 7612201 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2624. Min Act: -0.1700
Data Index: 1691114 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6686. Min Range: -6.6686
Max Act: 6.2311. Min Act: -0.1700
Data Index: 7124589 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19