Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 706 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.8060. Min Act: -0.1700
Data Index: 1144682 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.7435. Min Act: -0.1700
Data Index: 5480645 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.6497. Min Act: -0.1700
Data Index: 5230233 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6494187 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.6185. Min Act: -0.1700
Data Index: 1848408 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.5872. Min Act: -0.1700
Data Index: 8380394 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.6497. Min Act: -0.1700
Data Index: 5480644 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.5872. Min Act: -0.1700
Data Index: 5537291 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.6185. Min Act: -0.1700
Data Index: 7470472 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.5560. Min Act: -0.1700
Data Index: 6881608 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.5247. Min Act: -0.1700
Data Index: 8425235 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4622. Min Act: -0.1700
Data Index: 4823754 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4935. Min Act: -0.1700
Data Index: 6178202 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4935. Min Act: -0.1700
Data Index: 4690161 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4935. Min Act: -0.1700
Data Index: 4549135 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4622. Min Act: -0.1700
Data Index: 5331204 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4622. Min Act: -0.1700
Data Index: 6406095 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4310. Min Act: -0.1700
Data Index: 7325005 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4622. Min Act: -0.1700
Data Index: 4027998 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8060. Min Range: -6.8060
Max Act: 6.4622. Min Act: -0.1700
Data Index: 7460560 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19