Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3310 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.5246. Min Act: -0.1700
Data Index: 7557152 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.1809. Min Act: -0.1700
Data Index: 3306376 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.0871. Min Act: -0.1700
Data Index: 3798492 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.1184. Min Act: -0.1700
Data Index: 5565954 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.0559. Min Act: -0.1700
Data Index: 2966837 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.0246. Min Act: -0.1700
Data Index: 5067786 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5246. Min Range: -5.5246
Max Act: 5.0559. Min Act: -0.1700
Data Index: 6442247 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.9621. Min Act: -0.1700
Data Index: 7557153 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.9621. Min Act: -0.1700
Data Index: 1673671 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.9309. Min Act: -0.1700
Data Index: 7564897 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.9309. Min Act: -0.1700
Data Index: 269051 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8684. Min Act: -0.1700
Data Index: 4488239 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8371. Min Act: -0.1700
Data Index: 3571116 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8059. Min Act: -0.1700
Data Index: 8275851 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8059. Min Act: -0.1700
Data Index: 6540458 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.7746. Min Act: -0.1700
Data Index: 5315090 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8059. Min Act: -0.1700
Data Index: 7784627 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8059. Min Act: -0.1700
Data Index: 6631756 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.8059. Min Act: -0.1700
Data Index: 1289380 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5246. Min Range: -5.5246
Max Act: 4.7434. Min Act: -0.1700
Data Index: 5962087 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19