Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4951. Min Act: -0.1700
Data Index: 5758106 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4639. Min Act: -0.1700
Data Index: 2717859 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4639. Min Act: -0.1700
Data Index: 1208147 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4951. Min Act: -0.1700
Data Index: 4673011 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4326. Min Act: -0.1700
Data Index: 3586355 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4326. Min Act: -0.1700
Data Index: 1579721 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4326. Min Act: -0.1700
Data Index: 2009890 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.3389. Min Act: -0.1700
Data Index: 1145279 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.3076. Min Act: -0.1700
Data Index: 8329350 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2764. Min Act: -0.1700
Data Index: 5405880 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.3076. Min Act: -0.1700
Data Index: 5504455 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2451. Min Act: -0.1700
Data Index: 7650883 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2451. Min Act: -0.1700
Data Index: 4524807 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2139. Min Act: -0.1700
Data Index: 7063277 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2451. Min Act: -0.1700
Data Index: 3692290 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2764. Min Act: -0.1700
Data Index: 1323647 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2139. Min Act: -0.1700
Data Index: 802828 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2451. Min Act: -0.1700
Data Index: 1323650 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2139. Min Act: -0.1700
Data Index: 3920425 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2451. Min Act: -0.1700
Data Index: 5551055 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19