Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1461 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.7658. Min Act: -0.1700
Data Index: 2342448 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.7339. Min Act: -0.1700
Data Index: 5801260 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.7179. Min Act: -0.1700
Data Index: 1732368 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.6699. Min Act: -0.1700
Data Index: 2120807 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.6378. Min Act: -0.1700
Data Index: 404588 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.6378. Min Act: -0.1700
Data Index: 6254657 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.6056. Min Act: -0.1700
Data Index: 6254656 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5895. Min Act: -0.1700
Data Index: 3673854 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.6056. Min Act: -0.1700
Data Index: 5979916 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5573. Min Act: -0.1700
Data Index: 6167277 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5734. Min Act: -0.1700
Data Index: 4916211 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5734. Min Act: -0.1700
Data Index: 2962387 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5573. Min Act: -0.1700
Data Index: 7164205 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5411. Min Act: -0.1700
Data Index: 3884325 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5573. Min Act: -0.1700
Data Index: 2254432 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5573. Min Act: -0.1700
Data Index: 3897674 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5411. Min Act: -0.1700
Data Index: 6825584 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5734. Min Act: -0.1700
Data Index: 1737402 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5573. Min Act: -0.1700
Data Index: 4425843 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7658. Min Range: -2.7658
Max Act: 2.5250. Min Act: -0.1700
Data Index: 5858853 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19