Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0175. Min Range: -8.0175
Max Act: 8.0175. Min Act: -0.1700
Data Index: 5206731 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.8613. Min Act: -0.1700
Data Index: 1807454 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.8613. Min Act: -0.1700
Data Index: 3352727 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.7363. Min Act: -0.1700
Data Index: 143539 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.7675. Min Act: -0.1700
Data Index: 4159213 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.6738. Min Act: -0.1700
Data Index: 5119242 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.7363. Min Act: -0.1700
Data Index: 3873805 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.6738. Min Act: -0.1700
Data Index: 1864724 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.6113. Min Act: -0.1700
Data Index: 3064486 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.5488. Min Act: -0.1700
Data Index: 7363363 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.5488. Min Act: -0.1700
Data Index: 6052237 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.5488. Min Act: -0.1700
Data Index: 2796705 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.5175. Min Act: -0.1700
Data Index: 1527955 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.4550. Min Act: -0.1700
Data Index: 2606460 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.3925. Min Act: -0.1700
Data Index: 8816829 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.3613. Min Act: -0.1700
Data Index: 4068926 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.2988. Min Act: -0.1700
Data Index: 492003 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.2675. Min Act: -0.1700
Data Index: 3818338 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.2050. Min Act: -0.1700
Data Index: 2842310 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0175. Min Range: -8.0175
Max Act: 7.1738. Min Act: -0.1700
Data Index: 1075072 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19