Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 2066865 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 417937 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.4672. Min Act: -0.1700
Data Index: 2811813 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.4047. Min Act: -0.1700
Data Index: 7915051 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.4047. Min Act: -0.1700
Data Index: 3348705 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.3422. Min Act: -0.1700
Data Index: 7488993 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2797. Min Act: -0.1700
Data Index: 4496725 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2797. Min Act: -0.1700
Data Index: 2400452 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.3110. Min Act: -0.1700
Data Index: 3067358 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2797. Min Act: -0.1700
Data Index: 357231 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2485. Min Act: -0.1700
Data Index: 2388747 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2797. Min Act: -0.1700
Data Index: 7488995 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2797. Min Act: -0.1700
Data Index: 5289757 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2485. Min Act: -0.1700
Data Index: 8618599 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2485. Min Act: -0.1700
Data Index: 4220771 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2485. Min Act: -0.1700
Data Index: 2409361 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2172. Min Act: -0.1700
Data Index: 4732876 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2485. Min Act: -0.1700
Data Index: 197819 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2172. Min Act: -0.1700
Data Index: 8121721 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5297. Min Range: -5.5297
Max Act: 5.2485. Min Act: -0.1700
Data Index: 7214114 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19