Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5877. Min Act: -0.1700
Data Index: 3942255 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5877. Min Act: -0.1700
Data Index: 3942265 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5252. Min Act: -0.1700
Data Index: 1986951 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4939. Min Act: -0.1700
Data Index: 4491165 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4002. Min Act: -0.1700
Data Index: 970804 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4002. Min Act: -0.1700
Data Index: 249890 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4002. Min Act: -0.1700
Data Index: 3120198 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3689. Min Act: -0.1700
Data Index: 7348978 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3689. Min Act: -0.1700
Data Index: 4114180 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3377. Min Act: -0.1700
Data Index: 4114183 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3064. Min Act: -0.1700
Data Index: 1819100 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3064. Min Act: -0.1700
Data Index: 2555234 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3064. Min Act: -0.1700
Data Index: 2167550 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2752. Min Act: -0.1700
Data Index: 8523959 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3064. Min Act: -0.1700
Data Index: 4924223 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.3064. Min Act: -0.1700
Data Index: 2395070 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2752. Min Act: -0.1700
Data Index: 5061327 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2439. Min Act: -0.1700
Data Index: 1806486 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2752. Min Act: -0.1700
Data Index: 7928467 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2127. Min Act: -0.1700
Data Index: 8215807 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19