Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.3985. Min Act: -0.1700
Data Index: 1026445 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.3360. Min Act: -0.1700
Data Index: 3644859 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.3048. Min Act: -0.1700
Data Index: 6373074 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.2423. Min Act: -0.1700
Data Index: 2273291 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.2423. Min Act: -0.1700
Data Index: 2273293 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.2423. Min Act: -0.1700
Data Index: 5447535 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.1485. Min Act: -0.1700
Data Index: 3352907 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.1485. Min Act: -0.1700
Data Index: 835826 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.1485. Min Act: -0.1700
Data Index: 8225467 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.1173. Min Act: -0.1700
Data Index: 1534011 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.1173. Min Act: -0.1700
Data Index: 4171461 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.1173. Min Act: -0.1700
Data Index: 5052659 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0548. Min Act: -0.1700
Data Index: 179376 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0235. Min Act: -0.1700
Data Index: 2364263 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0235. Min Act: -0.1700
Data Index: 4652654 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0548. Min Act: -0.1700
Data Index: 2472391 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0548. Min Act: -0.1700
Data Index: 7690333 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0548. Min Act: -0.1700
Data Index: 1311948 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0235. Min Act: -0.1700
Data Index: 1111840 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3985. Min Range: -5.3985
Max Act: 5.0548. Min Act: -0.1700
Data Index: 592329 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19