Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.9643. Min Act: -0.1700
Data Index: 8471198 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.8393. Min Act: -0.1700
Data Index: 3453097 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.7768. Min Act: -0.1700
Data Index: 1206298 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.7768. Min Act: -0.1700
Data Index: 3162983 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.7768. Min Act: -0.1700
Data Index: 3474713 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.7143. Min Act: -0.1700
Data Index: 3453100 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.6205. Min Act: -0.1700
Data Index: 3453095 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.6205. Min Act: -0.1700
Data Index: 3655088 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.5893. Min Act: -0.1700
Data Index: 4298841 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.6205. Min Act: -0.1700
Data Index: 700204 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.5893. Min Act: -0.1700
Data Index: 6150459 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4643. Min Act: -0.1700
Data Index: 1540124 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4643. Min Act: -0.1700
Data Index: 8360671 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4018. Min Act: -0.1700
Data Index: 5551144 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4330. Min Act: -0.1700
Data Index: 3453099 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4643. Min Act: -0.1700
Data Index: 3453096 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4018. Min Act: -0.1700
Data Index: 2823083 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4018. Min Act: -0.1700
Data Index: 5551141 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4018. Min Act: -0.1700
Data Index: 3453092 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9643. Min Range: -5.9643
Max Act: 5.4018. Min Act: -0.1700
Data Index: 302496 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19