Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.2844. Min Act: -0.1700
Data Index: 3222442 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.2844. Min Act: -0.1700
Data Index: 4196677 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.1594. Min Act: -0.1700
Data Index: 3814585 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.1594. Min Act: -0.1700
Data Index: 5060781 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.1281. Min Act: -0.1700
Data Index: 4122029 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.0656. Min Act: -0.1700
Data Index: 3083902 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2844. Min Range: -7.2844
Max Act: 7.0031. Min Act: -0.1700
Data Index: 3713091 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.9406. Min Act: -0.1700
Data Index: 6082658 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.9406. Min Act: -0.1700
Data Index: 3457360 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.8469. Min Act: -0.1700
Data Index: 1843534 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.8156. Min Act: -0.1700
Data Index: 690900 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.8156. Min Act: -0.1700
Data Index: 6566401 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.8156. Min Act: -0.1700
Data Index: 632238 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7844. Min Act: -0.1700
Data Index: 6320363 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7844. Min Act: -0.1700
Data Index: 4359429 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7844. Min Act: -0.1700
Data Index: 6916118 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7844. Min Act: -0.1700
Data Index: 5867551 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7531. Min Act: -0.1700
Data Index: 5544339 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7219. Min Act: -0.1700
Data Index: 5252793 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2844. Min Range: -7.2844
Max Act: 6.7219. Min Act: -0.1700
Data Index: 5493840 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19