Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1668 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.1806. Min Act: -0.1700
Data Index: 7010910 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.1494. Min Act: -0.1700
Data Index: 6625266 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.1494. Min Act: -0.1700
Data Index: 6600513 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0869. Min Act: -0.1700
Data Index: 2556065 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0556. Min Act: -0.1700
Data Index: 4018887 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0869. Min Act: -0.1700
Data Index: 4255556 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0556. Min Act: -0.1700
Data Index: 8280252 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0556. Min Act: -0.1700
Data Index: 325801 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0243. Min Act: -0.1700
Data Index: 3315990 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0556. Min Act: -0.1700
Data Index: 5276206 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9931. Min Act: -0.1700
Data Index: 74970 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9931. Min Act: -0.1700
Data Index: 5645166 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0556. Min Act: -0.1700
Data Index: 359577 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9618. Min Act: -0.1700
Data Index: 5896038 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9931. Min Act: -0.1700
Data Index: 5331266 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0243. Min Act: -0.1700
Data Index: 7364465 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9618. Min Act: -0.1700
Data Index: 6800722 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9931. Min Act: -0.1700
Data Index: 422296 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0556. Min Act: -0.1700
Data Index: 5833049 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9618. Min Act: -0.1700
Data Index: 3622839 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19