Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.5703. Min Act: -0.1700
Data Index: 1248446 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.5546. Min Act: -0.1700
Data Index: 4796382 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.5076. Min Act: -0.1700
Data Index: 8402664 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.5233. Min Act: -0.1700
Data Index: 353223 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4606. Min Act: -0.1700
Data Index: 5781813 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4606. Min Act: -0.1700
Data Index: 1676145 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4606. Min Act: -0.1700
Data Index: 1468981 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4606. Min Act: -0.1700
Data Index: 6076367 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4450. Min Act: -0.1700
Data Index: 201168 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4606. Min Act: -0.1700
Data Index: 4446904 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4450. Min Act: -0.1700
Data Index: 4438562 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4136. Min Act: -0.1700
Data Index: 4477070 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4293. Min Act: -0.1700
Data Index: 4230474 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4136. Min Act: -0.1700
Data Index: 2640890 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4293. Min Act: -0.1700
Data Index: 5324824 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.3979. Min Act: -0.1700
Data Index: 8283884 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.4136. Min Act: -0.1700
Data Index: 5051512 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.3979. Min Act: -0.1700
Data Index: 1258640 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.3666. Min Act: -0.1700
Data Index: 4558746 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5703. Min Range: -3.5703
Max Act: 3.3823. Min Act: -0.1700
Data Index: 5324822 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19