Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7590. Min Act: -0.1700
Data Index: 8594012 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7277. Min Act: -0.1700
Data Index: 6193041 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7277. Min Act: -0.1700
Data Index: 663728 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7277. Min Act: -0.1700
Data Index: 244309 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6964. Min Act: -0.1700
Data Index: 5371958 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6964. Min Act: -0.1700
Data Index: 8463181 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6651. Min Act: -0.1700
Data Index: 1591534 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6339. Min Act: -0.1700
Data Index: 7563433 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6339. Min Act: -0.1700
Data Index: 5766925 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6651. Min Act: -0.1700
Data Index: 4895088 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6339. Min Act: -0.1700
Data Index: 5928432 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6339. Min Act: -0.1700
Data Index: 2339855 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6339. Min Act: -0.1700
Data Index: 6035491 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 376573 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 3062287 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 5608019 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 2566217 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 6248900 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 902888 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6026. Min Act: -0.1700
Data Index: 5034413 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19