Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.4011. Min Act: -0.1700
Data Index: 5853280 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.3698. Min Act: -0.1700
Data Index: 1177191 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.3073. Min Act: -0.1700
Data Index: 8686843 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.3386. Min Act: -0.1700
Data Index: 295205 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2761. Min Act: -0.1700
Data Index: 5667520 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2761. Min Act: -0.1700
Data Index: 5604452 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2448. Min Act: -0.1700
Data Index: 4118512 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2448. Min Act: -0.1700
Data Index: 6079619 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2448. Min Act: -0.1700
Data Index: 2108989 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2448. Min Act: -0.1700
Data Index: 1854493 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.2136. Min Act: -0.1700
Data Index: 1488293 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1823. Min Act: -0.1700
Data Index: 3672492 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1823. Min Act: -0.1700
Data Index: 1166082 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1823. Min Act: -0.1700
Data Index: 5102933 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1511. Min Act: -0.1700
Data Index: 3123264 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1823. Min Act: -0.1700
Data Index: 593539 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1511. Min Act: -0.1700
Data Index: 447563 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1198. Min Act: -0.1700
Data Index: 5657054 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1198. Min Act: -0.1700
Data Index: 4673480 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4011. Min Range: -5.4011
Max Act: 5.1198. Min Act: -0.1700
Data Index: 295202 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19