Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2273. Min Range: -5.2273
Max Act: 5.2273. Min Act: -0.1700
Data Index: 4498989 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.9148. Min Act: -0.1700
Data Index: 3852047 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.8836. Min Act: -0.1700
Data Index: 6724380 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7898. Min Act: -0.1700
Data Index: 4979444 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7586. Min Act: -0.1700
Data Index: 3925342 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7273. Min Act: -0.1700
Data Index: 6766176 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7273. Min Act: -0.1700
Data Index: 914989 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7273. Min Act: -0.1700
Data Index: 1209881 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7273. Min Act: -0.1700
Data Index: 1371689 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7273. Min Act: -0.1700
Data Index: 1599302 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.7273. Min Act: -0.1700
Data Index: 103003 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6961. Min Act: -0.1700
Data Index: 5381538 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1190095 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6961. Min Act: -0.1700
Data Index: 3852054 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6648. Min Act: -0.1700
Data Index: 956497 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6648. Min Act: -0.1700
Data Index: 1433357 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6336. Min Act: -0.1700
Data Index: 4245217 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6648. Min Act: -0.1700
Data Index: 2395059 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6336. Min Act: -0.1700
Data Index: 5576495 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2273. Min Range: -5.2273
Max Act: 4.6336. Min Act: -0.1700
Data Index: 526965 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19