Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.6154. Min Act: -0.1700
Data Index: 3448700 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.3654. Min Act: -0.1700
Data Index: 34501 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.3654. Min Act: -0.1700
Data Index: 4531798 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.2091. Min Act: -0.1700
Data Index: 3134592 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.1466. Min Act: -0.1700
Data Index: 5954164 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.1154. Min Act: -0.1700
Data Index: 5418501 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0529. Min Act: -0.1700
Data Index: 3974431 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0529. Min Act: -0.1700
Data Index: 1250099 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0216. Min Act: -0.1700
Data Index: 6775275 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 4165729 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 2363229 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6154. Min Range: -6.6154
Max Act: 6.0216. Min Act: -0.1700
Data Index: 6797707 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 486102 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9904. Min Act: -0.1700
Data Index: 8478591 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9591. Min Act: -0.1700
Data Index: 6345004 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.9279. Min Act: -0.1700
Data Index: 4668017 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.8966. Min Act: -0.1700
Data Index: 2008311 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.8966. Min Act: -0.1700
Data Index: 4759301 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.8966. Min Act: -0.1700
Data Index: 3735099 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6154. Min Range: -6.6154
Max Act: 5.8966. Min Act: -0.1700
Data Index: 7021868 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19