Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5585 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.8457. Min Act: -0.1700
Data Index: 7675888 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.7519. Min Act: -0.1700
Data Index: 5569628 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.7519. Min Act: -0.1700
Data Index: 2326369 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6894. Min Act: -0.1700
Data Index: 3094396 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6582. Min Act: -0.1700
Data Index: 1751175 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6582. Min Act: -0.1700
Data Index: 4799838 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6582. Min Act: -0.1700
Data Index: 7393120 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6582. Min Act: -0.1700
Data Index: 162147 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6269. Min Act: -0.1700
Data Index: 1439718 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6269. Min Act: -0.1700
Data Index: 8240820 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5957. Min Act: -0.1700
Data Index: 83076 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.6269. Min Act: -0.1700
Data Index: 4670246 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5644. Min Act: -0.1700
Data Index: 353150 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5957. Min Act: -0.1700
Data Index: 6974561 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5957. Min Act: -0.1700
Data Index: 3946493 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5644. Min Act: -0.1700
Data Index: 8188720 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5644. Min Act: -0.1700
Data Index: 1932719 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5332. Min Act: -0.1700
Data Index: 6177350 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5332. Min Act: -0.1700
Data Index: 2819777 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8457. Min Range: -5.8457
Max Act: 5.5332. Min Act: -0.1700
Data Index: 6436385 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19