Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 752 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.8552. Min Act: -0.1700
Data Index: 2476890 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.8552. Min Act: -0.1700
Data Index: 182303 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2222427 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.7302. Min Act: -0.1700
Data Index: 7475110 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.6364. Min Act: -0.1700
Data Index: 1931771 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.5739. Min Act: -0.1700
Data Index: 2811617 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.5427. Min Act: -0.1700
Data Index: 1191570 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1291881 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.5114. Min Act: -0.1700
Data Index: 6608629 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.4489. Min Act: -0.1700
Data Index: 1336683 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.4177. Min Act: -0.1700
Data Index: 1528191 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1727607 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.4489. Min Act: -0.1700
Data Index: 2095120 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.4489. Min Act: -0.1700
Data Index: 7438314 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.4489. Min Act: -0.1700
Data Index: 3005118 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.3864. Min Act: -0.1700
Data Index: 7221325 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.3864. Min Act: -0.1700
Data Index: 5871996 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.3864. Min Act: -0.1700
Data Index: 441633 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.3864. Min Act: -0.1700
Data Index: 3487904 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8552. Min Range: -5.8552
Max Act: 5.4177. Min Act: -0.1700
Data Index: 1285211 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19