Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2675. Min Range: -7.2675
Max Act: 7.2675. Min Act: -0.1700
Data Index: 6224620 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.8613. Min Act: -0.1700
Data Index: 2697030 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.8300. Min Act: -0.1700
Data Index: 1627965 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.7050. Min Act: -0.1700
Data Index: 5365162 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.7050. Min Act: -0.1700
Data Index: 5898622 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.6425. Min Act: -0.1700
Data Index: 4596376 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.5488. Min Act: -0.1700
Data Index: 3543293 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.5488. Min Act: -0.1700
Data Index: 7271068 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.5488. Min Act: -0.1700
Data Index: 1832061 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.5175. Min Act: -0.1700
Data Index: 7725431 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4863. Min Act: -0.1700
Data Index: 6775525 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4863. Min Act: -0.1700
Data Index: 1795981 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4550. Min Act: -0.1700
Data Index: 6132950 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4863. Min Act: -0.1700
Data Index: 328546 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4238. Min Act: -0.1700
Data Index: 2852089 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4238. Min Act: -0.1700
Data Index: 7282544 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.3925. Min Act: -0.1700
Data Index: 1055036 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4550. Min Act: -0.1700
Data Index: 2495068 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.4550. Min Act: -0.1700
Data Index: 2039829 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2675. Min Range: -7.2675
Max Act: 6.3925. Min Act: -0.1700
Data Index: 2850141 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19