Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.2696. Min Act: -0.1700
Data Index: 6775386 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.1758. Min Act: -0.1700
Data Index: 7933021 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.2071. Min Act: -0.1700
Data Index: 656451 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.1133. Min Act: -0.1700
Data Index: 4317675 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.1133. Min Act: -0.1700
Data Index: 929077 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.1446. Min Act: -0.1700
Data Index: 3750820 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.0195. Min Act: -0.1700
Data Index: 2321520 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.0195. Min Act: -0.1700
Data Index: 5567254 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2696. Min Range: -4.2696
Max Act: 4.0195. Min Act: -0.1700
Data Index: 2910718 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9883. Min Act: -0.1700
Data Index: 6922119 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9570. Min Act: -0.1700
Data Index: 1739821 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9883. Min Act: -0.1700
Data Index: 4795993 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9883. Min Act: -0.1700
Data Index: 7944892 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9570. Min Act: -0.1700
Data Index: 5411246 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9570. Min Act: -0.1700
Data Index: 3919058 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9258. Min Act: -0.1700
Data Index: 4067375 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.8945. Min Act: -0.1700
Data Index: 996364 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.8945. Min Act: -0.1700
Data Index: 8612478 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.8945. Min Act: -0.1700
Data Index: 5939373 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2696. Min Range: -4.2696
Max Act: 3.9258. Min Act: -0.1700
Data Index: 1971215 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19