Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.9897. Min Act: -0.1700
Data Index: 3074115 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.9897. Min Act: -0.1700
Data Index: 8204235 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.8647. Min Act: -0.1700
Data Index: 4229248 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.7397. Min Act: -0.1700
Data Index: 4760135 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.6772. Min Act: -0.1700
Data Index: 3879797 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.6147. Min Act: -0.1700
Data Index: 3497347 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.6459. Min Act: -0.1700
Data Index: 8480171 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.5834. Min Act: -0.1700
Data Index: 861036 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.5834. Min Act: -0.1700
Data Index: 4382768 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.5834. Min Act: -0.1700
Data Index: 4497294 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.5522. Min Act: -0.1700
Data Index: 5409379 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.5522. Min Act: -0.1700
Data Index: 4659658 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4897. Min Act: -0.1700
Data Index: 2821699 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.5209. Min Act: -0.1700
Data Index: 8725488 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4584. Min Act: -0.1700
Data Index: 8721938 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4584. Min Act: -0.1700
Data Index: 5839710 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4584. Min Act: -0.1700
Data Index: 5699206 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4272. Min Act: -0.1700
Data Index: 8536124 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4272. Min Act: -0.1700
Data Index: 3525999 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9897. Min Range: -6.9897
Max Act: 6.4272. Min Act: -0.1700
Data Index: 2527071 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19