Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.4585. Min Act: -0.1700
Data Index: 5015681 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.4271. Min Act: -0.1700
Data Index: 7937240 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.4271. Min Act: -0.1700
Data Index: 2720379 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3958. Min Act: -0.1700
Data Index: 1853261 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3958. Min Act: -0.1700
Data Index: 7824778 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3801. Min Act: -0.1700
Data Index: 498228 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3801. Min Act: -0.1700
Data Index: 7305732 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3644. Min Act: -0.1700
Data Index: 1243700 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3487. Min Act: -0.1700
Data Index: 7732855 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3487. Min Act: -0.1700
Data Index: 2033720 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3487. Min Act: -0.1700
Data Index: 2488155 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3487. Min Act: -0.1700
Data Index: 7129870 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 1101011 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 1696948 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 2499498 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 6819640 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 2473960 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 5726259 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 5611107 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4585. Min Range: -3.4585
Max Act: 3.3330. Min Act: -0.1700
Data Index: 5556318 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19