Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.4019. Min Act: -0.1700
Data Index: 894351 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.2144. Min Act: -0.1700
Data Index: 1541795 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.2144. Min Act: -0.1700
Data Index: 5024143 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.1207. Min Act: -0.1700
Data Index: 5832247 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.1207. Min Act: -0.1700
Data Index: 8285959 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.1207. Min Act: -0.1700
Data Index: 3820233 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.0582. Min Act: -0.1700
Data Index: 2244579 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4019. Min Range: -7.4019
Max Act: 7.0582. Min Act: -0.1700
Data Index: 6348147 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.9957. Min Act: -0.1700
Data Index: 8276840 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.9332. Min Act: -0.1700
Data Index: 4907387 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.9332. Min Act: -0.1700
Data Index: 5052349 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.9019. Min Act: -0.1700
Data Index: 6684243 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.8082. Min Act: -0.1700
Data Index: 1950711 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.7769. Min Act: -0.1700
Data Index: 3905800 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.7769. Min Act: -0.1700
Data Index: 6260226 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.8082. Min Act: -0.1700
Data Index: 1052290 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.7457. Min Act: -0.1700
Data Index: 7418001 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.7457. Min Act: -0.1700
Data Index: 5467313 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.7457. Min Act: -0.1700
Data Index: 8655459 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4019. Min Range: -7.4019
Max Act: 6.7144. Min Act: -0.1700
Data Index: 7058363 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19