Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2249. Min Range: -9.2249
Max Act: 9.2249. Min Act: -0.1700
Data Index: 2266768 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2249. Min Range: -9.2249
Max Act: 9.0999. Min Act: -0.1700
Data Index: 5773668 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2249. Min Range: -9.2249
Max Act: 9.0374. Min Act: -0.1700
Data Index: 8468504 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2249. Min Range: -9.2249
Max Act: 9.0999. Min Act: -0.1700
Data Index: 96732 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.8499. Min Act: -0.1700
Data Index: 1080747 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.8499. Min Act: -0.1700
Data Index: 7038332 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.8499. Min Act: -0.1700
Data Index: 1824748 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.7249. Min Act: -0.1700
Data Index: 3789997 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.7874. Min Act: -0.1700
Data Index: 3009103 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.7874. Min Act: -0.1700
Data Index: 3373660 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.6624. Min Act: -0.1700
Data Index: 6773953 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.7249. Min Act: -0.1700
Data Index: 8666526 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.7249. Min Act: -0.1700
Data Index: 1151259 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.6624. Min Act: -0.1700
Data Index: 4552128 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.6624. Min Act: -0.1700
Data Index: 2040408 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.6624. Min Act: -0.1700
Data Index: 3093436 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.6624. Min Act: -0.1700
Data Index: 2489407 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.6624. Min Act: -0.1700
Data Index: 744837 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.5374. Min Act: -0.1700
Data Index: 7019355 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2249. Min Range: -9.2249
Max Act: 8.5999. Min Act: -0.1700
Data Index: 7570187 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19