Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 83 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1450. Min Range: -7.1450
Max Act: 7.1450. Min Act: -0.1700
Data Index: 258501 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.8950. Min Act: -0.1700
Data Index: 3508899 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.8325. Min Act: -0.1700
Data Index: 4838367 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.8325. Min Act: -0.1700
Data Index: 1110663 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.7700. Min Act: -0.1700
Data Index: 6958260 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.7387. Min Act: -0.1700
Data Index: 4771255 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.7075. Min Act: -0.1700
Data Index: 5152672 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.7387. Min Act: -0.1700
Data Index: 2913312 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.6137. Min Act: -0.1700
Data Index: 5732828 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1445107 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4610628 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.5200. Min Act: -0.1700
Data Index: 6249876 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.5200. Min Act: -0.1700
Data Index: 3943226 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.4887. Min Act: -0.1700
Data Index: 7731494 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.4575. Min Act: -0.1700
Data Index: 3151524 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.4575. Min Act: -0.1700
Data Index: 6691563 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.4575. Min Act: -0.1700
Data Index: 2544217 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.4262. Min Act: -0.1700
Data Index: 3454901 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.4262. Min Act: -0.1700
Data Index: 6132206 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1450. Min Range: -7.1450
Max Act: 6.3950. Min Act: -0.1700
Data Index: 2507531 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19