Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.4550. Min Act: -0.1700
Data Index: 342776 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3735. Min Act: -0.1700
Data Index: 540520 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3735. Min Act: -0.1700
Data Index: 2252349 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3571. Min Act: -0.1700
Data Index: 4284262 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3571. Min Act: -0.1700
Data Index: 2725823 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3243. Min Act: -0.1700
Data Index: 6402811 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3079. Min Act: -0.1700
Data Index: 4147507 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.3243. Min Act: -0.1700
Data Index: 4679838 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2914. Min Act: -0.1700
Data Index: 6758806 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2749. Min Act: -0.1700
Data Index: 6399500 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2584. Min Act: -0.1700
Data Index: 7479996 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2584. Min Act: -0.1700
Data Index: 864799 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2749. Min Act: -0.1700
Data Index: 8771358 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2584. Min Act: -0.1700
Data Index: 8182728 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2254. Min Act: -0.1700
Data Index: 8790419 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2254. Min Act: -0.1700
Data Index: 6782913 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2088. Min Act: -0.1700
Data Index: 4443226 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.2088. Min Act: -0.1700
Data Index: 7404351 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.1922. Min Act: -0.1700
Data Index: 6280975 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4550. Min Range: -2.4550
Max Act: 2.1922. Min Act: -0.1700
Data Index: 8210527 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19