Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.5757. Min Act: -0.1700
Data Index: 1363518 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.5444. Min Act: -0.1700
Data Index: 5381609 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.5132. Min Act: -0.1700
Data Index: 7845122 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.3882. Min Act: -0.1700
Data Index: 2692376 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.3569. Min Act: -0.1700
Data Index: 4291103 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.3569. Min Act: -0.1700
Data Index: 2860367 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.3257. Min Act: -0.1700
Data Index: 6743223 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.3257. Min Act: -0.1700
Data Index: 334496 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.3257. Min Act: -0.1700
Data Index: 2755689 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2944. Min Act: -0.1700
Data Index: 6690533 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2944. Min Act: -0.1700
Data Index: 6187063 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4914731 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2319. Min Act: -0.1700
Data Index: 7670843 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2632. Min Act: -0.1700
Data Index: 6333748 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2632. Min Act: -0.1700
Data Index: 2420335 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2632. Min Act: -0.1700
Data Index: 8052239 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2632. Min Act: -0.1700
Data Index: 7637819 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2632. Min Act: -0.1700
Data Index: 8255379 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2632. Min Act: -0.1700
Data Index: 7117460 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5757. Min Range: -5.5757
Max Act: 5.2319. Min Act: -0.1700
Data Index: 2699848 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19