Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4185. Min Range: -8.4185
Max Act: 8.4185. Min Act: -0.1700
Data Index: 6603344 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4185. Min Range: -8.4185
Max Act: 8.0435. Min Act: -0.1700
Data Index: 2437075 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.6998. Min Act: -0.1700
Data Index: 7185854 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.5123. Min Act: -0.1700
Data Index: 16705 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.4810. Min Act: -0.1700
Data Index: 2239653 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.3560. Min Act: -0.1700
Data Index: 4143672 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.3248. Min Act: -0.1700
Data Index: 3021003 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2935. Min Act: -0.1700
Data Index: 5030802 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2935. Min Act: -0.1700
Data Index: 1151999 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2935. Min Act: -0.1700
Data Index: 4248919 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2623. Min Act: -0.1700
Data Index: 6894147 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2623. Min Act: -0.1700
Data Index: 6312216 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2935. Min Act: -0.1700
Data Index: 2600681 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2935. Min Act: -0.1700
Data Index: 7351476 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.2310. Min Act: -0.1700
Data Index: 3547041 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.1685. Min Act: -0.1700
Data Index: 132362 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.1373. Min Act: -0.1700
Data Index: 5942132 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.1060. Min Act: -0.1699
Data Index: 5935910 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.1060. Min Act: -0.1700
Data Index: 5899368 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4185. Min Range: -8.4185
Max Act: 7.1060. Min Act: -0.1700
Data Index: 5778124 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19