Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.3699. Min Act: -0.1700
Data Index: 4610790 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.2601. Min Act: -0.1700
Data Index: 6107525 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.2286. Min Act: -0.1700
Data Index: 3062509 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.2129. Min Act: -0.1700
Data Index: 6192775 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.2129. Min Act: -0.1700
Data Index: 5946326 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1972. Min Act: -0.1700
Data Index: 4398652 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1972. Min Act: -0.1700
Data Index: 4288990 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1815. Min Act: -0.1700
Data Index: 5999171 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1815. Min Act: -0.1700
Data Index: 1661025 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1657. Min Act: -0.1700
Data Index: 4230183 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1500. Min Act: -0.1700
Data Index: 3403769 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1657. Min Act: -0.1700
Data Index: 7376918 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1342. Min Act: -0.1700
Data Index: 1436321 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1027. Min Act: -0.1700
Data Index: 4142661 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1027. Min Act: -0.1700
Data Index: 1581361 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1185. Min Act: -0.1700
Data Index: 1013656 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.1027. Min Act: -0.1700
Data Index: 6290314 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.0870. Min Act: -0.1700
Data Index: 700007 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.0712. Min Act: -0.1700
Data Index: 5102501 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3699. Min Range: -3.3699
Max Act: 3.0712. Min Act: -0.1700
Data Index: 1179837 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19