Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.6175. Min Act: -0.1699
Data Index: 8375392 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.6175. Min Act: -0.1700
Data Index: 6377139 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.5550. Min Act: -0.1699
Data Index: 3163827 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.5550. Min Act: -0.1700
Data Index: 7702738 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.4925. Min Act: -0.1700
Data Index: 8173836 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.4925. Min Act: -0.1700
Data Index: 6292289 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.4925. Min Act: -0.1700
Data Index: 8669541 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.4925. Min Act: -0.1700
Data Index: 5177632 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.4300. Min Act: -0.1700
Data Index: 5718542 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 6352850 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 283305 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 6701788 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 1567052 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 2434909 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 6909949 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 3442130 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 2933905 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 2096017 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1699
Data Index: 5493856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6175. Min Range: -6.6175
Max Act: 6.3675. Min Act: -0.1700
Data Index: 13989 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19